{"id":"7900e0bf-9411-4215-b5e7-28274b60d708","entityType":"agent","slug":"clawhub-agentpmt-speech-to-text-with-speakers","name":"Speech To Text With Speakers","canonicalUrl":"https://www.xpersona.co/agent/clawhub-agentpmt-speech-to-text-with-speakers","canonicalPath":"/agent/clawhub-agentpmt-speech-to-text-with-speakers","generatedAt":"2026-10-13T01:47:17.496Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:22:50.548Z","emptyReason":null},"description":"Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an a...","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 955 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s17c4gq739k6px8k8sryevfm9h86myay:speech-to-text-with-speakers","sourceUrl":"https://clawhub.ai/agentpmt/speech-to-text-with-speakers","homepage":"https://clawhub.ai/agentpmt/skills/speech-to-text-with-speakers","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/agentpmt/speech-to-text-with-speakers","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/agentpmt/skills/speech-to-text-with-speakers","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Speech To Text With Speakers technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:22:50.548Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:22:50.548Z","emptyReason":null},"stars":null,"forks":null,"downloads":955,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.6","tractionLabel":"955 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:22:50.438Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T02:22:50.548Z","lastCrawledAt":"2026-10-12T02:22:50.438Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T02:22:50.438Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.6","createdAt":"2026-07-22T00:25:52.451Z","changelog":"Publish speech-to-text-with-speakers v1.0.6","fileCount":4,"zipByteSize":8419},{"version":"1.0.5","createdAt":"2026-07-21T14:04:09.319Z","changelog":"Publish speech-to-text-with-speakers v1.0.5","fileCount":4,"zipByteSize":7135},{"version":"1.0.4","createdAt":"2026-07-21T04:13:37.643Z","changelog":"Publish speech-to-text-with-speakers v1.0.4","fileCount":4,"zipByteSize":6962},{"version":"1.0.3","createdAt":"2026-07-21T04:05:29.851Z","changelog":"Publish speech-to-text-with-speakers v1.0.3","fileCount":4,"zipByteSize":6896},{"version":"1.0.2","createdAt":"2026-07-21T03:49:45.733Z","changelog":"Publish speech-to-text-with-speakers v1.0.2","fileCount":4,"zipByteSize":6853},{"version":"1.0.1","createdAt":"2026-07-21T03:13:19.746Z","changelog":"Publish speech-to-text-with-speakers v1.0.1","fileCount":4,"zipByteSize":7097},{"version":"1.0.0","createdAt":"2026-06-24T09:37:53.503Z","changelog":"Publish speech-to-text-with-speakers v1.0.0","fileCount":4,"zipByteSize":6769}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17c4gq739k6px8k8sryevfm9h86myay:speech-to-text-with-speakers","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s17c4gq739k6px8k8sryevfm9h86myay:speech-to-text-with-speakers` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/agentpmt/speech-to-text-with-speakers before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-13T01:47:17.494Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-agentpmt-speech-to-text-with-speakers/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T02:22:50.548Z","emptyReason":null},"readme":"Skill: Speech To Text With Speakers\n\nOwner: agentpmt\n\nSummary: Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an a...\n\nTags: agentpmt:1.0.6, get-task:1.0.6, latest:1.0.6, list-tasks:1.0.6, marketplace:1.0.6, transcribe-extended:1.0.6, transcribe-quick:1.0.6, transcribe-standard:1.0.6\n\nVersion history:\n\nv1.0.6 | 2026-07-22T00:25:52.451Z | user\n\nPublish speech-to-text-with-speakers v1.0.6\n\nv1.0.5 | 2026-07-21T14:04:09.319Z | user\n\nPublish speech-to-text-with-speakers v1.0.5\n\nv1.0.4 | 2026-07-21T04:13:37.643Z | user\n\nPublish speech-to-text-with-speakers v1.0.4\n\nv1.0.3 | 2026-07-21T04:05:29.851Z | user\n\nPublish speech-to-text-with-speakers v1.0.3\n\nv1.0.2 | 2026-07-21T03:49:45.733Z | user\n\nPublish speech-to-text-with-speakers v1.0.2\n\nv1.0.1 | 2026-07-21T03:13:19.746Z | user\n\nPublish speech-to-text-with-speakers v1.0.1\n\nv1.0.0 | 2026-06-24T09:37:53.503Z | user\n\nPublish speech-to-text-with-speakers v1.0.0\n\nArchive index:\n\nArchive v1.0.6: 4 files, 8419 bytes\n\nFiles: schema.md (13485b), skill-card.md (2632b), SKILL.md (15055b), _meta.json (147b)\n\nFile v1.0.6:SKILL.md\n\n---\nname: speech-to-text-with-speakers\ndescription: \"Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an agent needs speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, get task, task id, list tasks through AgentPMT-hosted remote tool calls. Discovery terms: speech to text with speakers, transcribe meeting recordings.\"\nversion: 1.0.6\nhomepage: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\ncompatibility: \"Agent instructions for AgentPMT-hosted remote tool calls. Follow this skill body for supported account, wallet, and setup routes. No local command runtime is declared.\"\nmetadata: {\"author\":\"agentpmt\",\"openclaw\":{\"homepage\":\"https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\"}}\n---\n# Speech to Text With Speakers\n\n## Freshness\nLast updated: `2026-07-22`.\n\nIf the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.\n\n## What This Tool Does\nTurn any audio recording into clean, searchable text in seconds. Transcribe voice memos, meetings, interviews, podcasts, and webinars with accurate speech recognition that handles accents and background noise. Get plain text for quick reference, SRT or WebVTT subtitles for video captioning, or rich JSON output with word-level timestamps and speaker identification. Choose from three tiers based on recording length — up to 15, 30, or 60 minutes — and optionally enable speaker diarization to label who said what, profanity filtering, and alternative transcripts for maximum accuracy.\n\n## Product Instructions\n### Speech to Text\n\nTranscribe audio with one tool. Transcribe actions run as background tasks: the submit response returns a `task_id` immediately, and short clips usually complete inline in that same response. Poll `get_task` for anything still processing.\n\n#### Tool Call Format\n\n```json\n{\n  \"action\": \"get_instructions\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_quick\",\n  \"file_id\": \"FILE_ID\",\n  \"language_code\": \"en-US\",\n  \"output_format\": \"text\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"public_url\": \"https://example.com/meeting.m4a\",\n  \"output_format\": \"vtt\",\n  \"enable_word_timestamps\": true,\n  \"enable_diarization\": true\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_extended\",\n  \"public_url\": \"https://example.com/interview.webm\",\n  \"output_format\": \"json\",\n  \"max_alternatives\": 2\n}\n```\n\n```json\n{\n  \"action\": \"get_task\",\n  \"task_id\": \"TASK_ID\"\n}\n```\n\n```json\n{\n  \"action\": \"list_tasks\",\n  \"limit\": 20\n}\n```\n\n#### Actions\n\n- `transcribe_quick`: audio up to 15 minutes. Price: 100 credits.\n- `transcribe_standard`: audio up to 30 minutes. Price: 150 credits.\n- `transcribe_extended`: audio up to 60 minutes. Price: 200 credits.\n- `get_task`: check a transcription task's progress and retrieve its result. Price: 1 credit.\n- `list_tasks`: list recent transcription tasks. Price: 1 credit.\n\n#### Async task flow\n\n- Every transcribe action returns a task envelope: `{action, task_id, status, ...}`. ALWAYS check `status` before polling — short clips finish within the submit request and return `status: \"completed\"` with `outputs` inline, costing zero polls.\n- When `status` is `\"processing\"`, poll `get_task` with the returned `task_id` every 10-15 seconds. `progress` advances as the job moves through download, validation, and recognition.\n- A completed task carries the full transcription payload in `outputs[0]`: the selected content inline (`text`, `srt_content`, `vtt_content`, or `json_data`), plus `speakers`, `word_count`, `confidence_score`, `audio_metadata`, and the File Manager artifact fields `result_file_id`/`result_signed_url`.\n- A failed task carries `error`. Tier-limit failures also carry `error_details` with `recommended_actions` — resubmit with the suggested larger tier.\n- If the service restarts mid-transcription, in-flight Google batch jobs resume automatically. Jobs that cannot resume are marked failed with an instruction to resubmit; they never sit in `processing` forever.\n\n#### Billing\n\n- Transcribe actions charge on submission. A task that later fails (for example, audio too long for the tier) is not auto-refunded — pick the tier from the recording length you already know, and check `error_details.recommended_actions` before resubmitting.\n\n#### Notes\n\n- Provide either `file_id` or `public_url`.\n- `public_url` must be an HTTPS URL and cannot point to private or internal network addresses.\n- Audio downloads are capped at 150MB. If a recording is larger, compress it to mp3 or m4a and retry.\n- If `language_code` is omitted, the tool defaults to `en-US`.\n- Supported output formats: `text`, `srt`, `vtt`, `json`.\n- Optional controls: `enable_diarization`, `enable_word_timestamps`, `remove_filler_words`, `enable_profanity_filter`, `max_alternatives`.\n- `remove_filler_words` defaults to `true`, which uses Google STT V2's cleaned transcript path.\n- Set `remove_filler_words` to `false` to preserve disfluencies through Vercel AI Gateway using the `openai/whisper-1` gateway model slug. This path always requests word-level timestamps from the gateway for clipping workflows.\n- `remove_filler_words=false` does not support `enable_diarization=true` or `max_alternatives` greater than `1`; use the default cleaned path for those features.\n- `enable_diarization=true` supports audio up to 20 minutes (a provider limit). Longer recordings fail with guidance: disable diarization, or split the audio into 20-minute segments and transcribe them individually.\n- With `enable_diarization=true`, `text` output is speaker-labelled one line per turn (`[0:04] Speaker 0: ...`), inline and in the stored `transcription.txt`, so it is readable without reformatting. Without diarization it is the flat transcript. Speaker numbers match the `speaker_tag` values in `speakers`/`json_data`.\n- During invocations with File Manager storage available, `text` and `json` results are stored for every successful transcription; `srt` and `vtt` results are stored when the generated subtitle content is non-empty. The corresponding filenames are `transcription.txt`, `transcription.json`, `transcription.srt`, and `transcription.vtt`.\n- Stored artifacts are returned through the `result_file_id` and `result_signed_url` fields in `outputs[0]`. Agents should use `result_file_id` for later File Manager operations.\n- If transcription succeeds but artifact storage fails, the inline result remains available and `result_file_error` explains that the File Manager file could not be created.\n\n## When To Use\n- Use this skill for `Speech to Text With Speakers` on AgentPMT.\n- Use it when an agent needs this specific tool's behavior, schema, inputs, outputs, and invocation shape.\n- Search and activation keywords: speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, get task, task id, list tasks.\n- Supported action names: `get_task`, `list_tasks`, `transcribe_extended`, `transcribe_quick`, `transcribe_standard`.\n\n## Use Cases\n- Transcribe meeting recordings\n- Generate subtitles and captions for videos\n- Convert voice memos to searchable text\n- Transcribe podcast episodes\n- Create interview transcripts with speaker labels\n- Produce SRT or WebVTT subtitle files\n- Build searchable audio archives\n- Transcribe webinars and lectures\n- Analyze customer call recordings\n- Content repurposing from audio to text\n\n## Related Product Skills\n- File Management: ../file-management (ClawHub: `file-management`, page: https://clawhub.ai/agentpmt/file-management; skills.sh: `npx skills add AgentPMT/agent-skills --skill file-management`)\n\n## Categories And Industries\nNo categories or industry tags are published for this tool.\n\n## Actions And Schema\nComplete generated action schema: `./schema.md`.\nSupported action count: `5`.\nx402 availability: not enabled for this product.\n\n- `get_task` (action slug: `get-task`): Check a transcription task's progress and retrieve its result. Completed tasks carry the full transcription payload in outputs[0]. Price: `1` credits. Parameters: `task_id`.\n- `list_tasks` (action slug: `list-tasks`): List recent transcription tasks with status and progress. Price: `1` credits. Parameters: `limit`.\n- `transcribe_extended` (action slug: `transcribe-extended`): Start an asynchronous transcription of audio up to 60 minutes. Returns a task_id immediately (short clips complete inline in the same response); poll get_task for the completed transcript and File Manager artifact. Price: `200` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_quick` (action slug: `transcribe-quick`): Start an asynchronous transcription of audio up to 15 minutes. Returns a task_id immediately (short clips complete inline in the same response); poll get_task for the completed transcript and File Manager artifact. Price: `100` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_standard` (action slug: `transcribe-standard`): Start an asynchronous transcription of audio up to 30 minutes. Returns a task_id immediately (short clips complete inline in the same response); poll get_task for the completed transcript and File Manager artifact. Price: `150` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n\n## Live Schema And Examples\nUse the compact schema above for ordinary calls. Before a new production integration, or whenever parameters, enum values, nested objects, outputs, or examples are unclear, fetch live details first.\n\n- Exact schema: call `agentpmt-tool-search-and-execution` with `action: \"get_schema\"`, and `tool_id: \"speech-to-text-with-speakers\"`.\n- Detailed examples: call `agentpmt-tool-search-and-execution` with `action: \"get_instructions\"` and `tool_id: \"speech-to-text-with-speakers\"`, or call this product with `action: \"get_instructions\"` when the product tool is already selected.\n- Treat returned live schema and instructions as more specific than this generated summary.\n\nMCP schema lookup through the main AgentPMT MCP server:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"AgentPMT-Tool-Search-and-Execution\",\n    \"arguments\": {\n      \"action\": \"get_schema\",\n      \"tool_id\": \"speech-to-text-with-speakers\"\n    }\n  }\n}\n```\n\nFor live examples, keep the same MCP tool and use these arguments:\n\n```json\n{\n  \"action\": \"get_instructions\",\n  \"tool_id\": \"speech-to-text-with-speakers\"\n}\n```\n\nAuthenticated AgentPMT REST schema lookup body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_schema\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\nAuthenticated AgentPMT REST live examples body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_instructions\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\n## Call This Tool\nProduct slug: `speech-to-text-with-speakers`\n\nMarketplace page: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n\n- AgentPMT account route: first use `../agentpmt-account-mcp-rest-api-setup` to connect the main MCP server or REST API for an Agent Group where this tool is enabled.\n- x402 route: not enabled for this product.\n- AgentPMT overview: use `../what-is-agentpmt` for marketplace, Agent Group, workflow, MCP, REST, and payment concepts.\n\nIf those setup skills are not installed beside this product skill, use the downloads below.\n\nCore AgentPMT setup skills:\n- What AgentPMT is: ../what-is-agentpmt\n  - ClawHub page: https://clawhub.ai/agentpmt/what-is-agentpmt\n  - OpenClaw install: `openclaw skills install what-is-agentpmt`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup\n  - ClawHub page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup\n  - OpenClaw install: `openclaw skills install agentpmt-account-mcp-rest-api-setup`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`\n\nskills.sh install script:\n\n```bash\nnpx skills add AgentPMT/agent-skills --skill what-is-agentpmt\nnpx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup\n```\n\nMCP call shape after the main AgentPMT MCP server is connected:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"Speech-to-Text-With-Speakers\",\n    \"arguments\": {\n      \"action\": \"get_task\",\n      \"task_id\": \"example task id\"\n    }\n  }\n}\n```\n\nUse the exact tool name returned by `tools/list`; the name above is the expected readable form.\n\nAuthenticated AgentPMT REST call body:\n\n```json\n{\n  \"name\": \"speech-to-text-with-speakers\",\n  \"parameters\": {\n    \"action\": \"get_task\",\n    \"task_id\": \"example task id\"\n  }\n}\n```\n\nUse the setup skill for the account connection details before making REST calls.\n\n## Response Handling\n- Treat the returned JSON as the source of truth for this tool call.\n- If the response includes warnings or correction targets, apply them before retrying.\n- If the response includes a `passed` or success-style boolean, use it as the workflow gate.\n- If validation fails or the response shape is unclear, call `get_schema` or `get_instructions` before retrying.\n- If `get_task` fails, preserve the request parameters and retry only after fixing schema, auth, or payment errors.\n\n## Security\n- Do not place account secrets, wallet private keys, mnemonics, signatures, or payment headers in prompts or logs.\n- Keep tool inputs scoped to the minimum content needed for the task.\n- Use the setup skills for credential handling; this product skill only defines product-specific behavior.\n\n## AgentPMT Reference\n- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)\n- Marketplace product: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n- AgentPMT main MCP server: https://api.agentpmt.com/mcp/\n- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase\n\nFile v1.0.6:_meta.json\n\n{\n  \"ownerId\": \"kn798pfbxm62kkd2750t7vsex5819pyc\",\n  \"slug\": \"speech-to-text-with-speakers\",\n  \"version\": \"1.0.6\",\n  \"publishedAt\": 1784679952451\n}\n\nFile v1.0.6:schema.md\n\n# Speech to Text With Speakers Schema\n\nThis generated reference belongs to the adjacent `SKILL.md`. Use it for exact action names, action slugs, parameter summaries, sample parameters, and generated JSON parameter schemas.\n\nProduct slug: `speech-to-text-with-speakers`\n\nx402 availability: not enabled for this product.\n\n## `get_task`\n\nAction slug: `get-task`\n\nPrice: `1` credits\n\nCheck a transcription task's progress and retrieve its result. Completed tasks carry the full transcription payload in outputs[0].\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `task_id` | `string` | yes | Task ID returned by a transcribe action. |\n\nSample parameters:\n\n```json\n{\n  \"task_id\": \"example task id\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"task_id\": {\n    \"description\": \"Task ID returned by a transcribe action.\",\n    \"required\": true,\n    \"type\": \"string\"\n  }\n}\n```\n\n## `list_tasks`\n\nAction slug: `list-tasks`\n\nPrice: `1` credits\n\nList recent transcription tasks with status and progress.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `limit` | `integer` | no | Maximum number of tasks to return. |\n\nSample parameters:\n\n```json\n{\n  \"limit\": 20\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"limit\": {\n    \"default\": 20,\n    \"description\": \"Maximum number of tasks to return.\",\n    \"maximum\": 100,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  }\n}\n```\n\n## `transcribe_extended`\n\nAction slug: `transcribe-extended`\n\nPrice: `200` credits\n\nStart an asynchronous transcription of audio up to 60 minutes. Returns a task_id immediately (short clips complete inline in the same response); poll get_task for the completed transcript and File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. The completed task's outputs include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. The completed task's outputs include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_quick`\n\nAction slug: `transcribe-quick`\n\nPrice: `100` credits\n\nStart an asynchronous transcription of audio up to 15 minutes. Returns a task_id immediately (short clips complete inline in the same response); poll get_task for the completed transcript and File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. The completed task's outputs include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. The completed task's outputs include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_standard`\n\nAction slug: `transcribe-standard`\n\nPrice: `150` credits\n\nStart an asynchronous transcription of audio up to 30 minutes. Returns a task_id immediately (short clips complete inline in the same response); poll get_task for the completed transcript and File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. The completed task's outputs include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. The completed task's outputs include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\nFile v1.0.6:skill-card.md\n\n## Description:\n\nTranscribes audio from an uploaded file_id or public HTTPS URL into text, SRT, WebVTT, or JSON with optional word timestamps, profanity filtering, alternatives, and speaker diarization through AgentPMT-hosted remote calls.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[agentpmt](https://clawhub.ai/user/agentpmt)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to submit meeting recordings, voice memos, interviews, podcasts, webinars, and similar audio for transcription, then poll task status and retrieve transcript outputs with optional speaker labels and timing data.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Audio supplied by file_id or public URL is processed by AgentPMT and transcription providers.\n\nMitigation: Avoid confidential or regulated recordings unless the user's organization permits that processing.\n\nRisk: npx-based setup steps may introduce supply-chain exposure.\n\nMitigation: Prefer the OpenClaw install route, or verify and pin setup dependencies before running npx commands.\n\nRisk: Selecting a tier below the recording length can fail after submission and may still consume credits.\n\nMitigation: Choose the tier from the known recording length and review error_details.recommended_actions before resubmitting.\n\n## Reference(s):\n\n- [Speech To Text With Speakers ClawHub Page](https://clawhub.ai/agentpmt/skills/speech-to-text-with-speakers)\n- [AgentPMT Marketplace Product](https://www.agentpmt.com/marketplace/speech-to-text-with-speakers)\n- [Speech To Text With Speakers Schema](artifact/schema.md)\n- [AgentPMT Account MCP/REST Setup](https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup)\n- [AgentPMT File Management](https://clawhub.ai/agentpmt/file-management)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, JSON, Configuration guidance]\n\n**Output Format:** [Markdown guidance with JSON tool-call examples; task outputs may include plain text, SRT, WebVTT, or structured JSON.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Transcription jobs run asynchronously; completed tasks can include inline transcript content, speaker data, timing metadata, and File Manager artifact identifiers.]\n\n## Skill Version(s):\n\n1.0.6 (source: frontmatter and server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.5: 4 files, 7135 bytes\n\nFiles: schema.md (12079b), skill-card.md (2739b), SKILL.md (12823b), _meta.json (147b)\n\nFile v1.0.5:SKILL.md\n\n---\nname: speech-to-text-with-speakers\ndescription: \"Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an agent needs speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, transcribe extended, file id, public url through AgentPMT-hosted remote tool calls. Discovery terms: speech to text with speakers.\"\nversion: 1.0.5\nhomepage: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\ncompatibility: \"Agent instructions for AgentPMT-hosted remote tool calls. Follow this skill body for supported account, wallet, and setup routes. No local command runtime is declared.\"\nmetadata: {\"author\":\"agentpmt\",\"openclaw\":{\"homepage\":\"https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\"}}\n---\n# Speech to Text With Speakers\n\n## Freshness\nLast updated: `2026-07-21`.\n\nIf the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.\n\n## What This Tool Does\nTurn any audio recording into clean, searchable text in seconds. Transcribe voice memos, meetings, interviews, podcasts, and webinars with accurate speech recognition that handles accents and background noise. Get plain text for quick reference, SRT or WebVTT subtitles for video captioning, or rich JSON output with word-level timestamps and speaker identification. Choose from three tiers based on recording length — up to 15, 30, or 60 minutes — and optionally enable speaker diarization to label who said what, profanity filtering, and alternative transcripts for maximum accuracy.\n\n## Product Instructions\n### Speech to Text\n\nTranscribe audio with one tool and choose the action that matches the upload length.\n\n#### Tool Call Format\n\n```json\n{\n  \"action\": \"get_instructions\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_quick\",\n  \"file_id\": \"FILE_ID\",\n  \"language_code\": \"en-US\",\n  \"output_format\": \"text\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"public_url\": \"https://example.com/meeting.m4a\",\n  \"output_format\": \"vtt\",\n  \"enable_word_timestamps\": true,\n  \"enable_diarization\": true\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_extended\",\n  \"public_url\": \"https://example.com/interview.webm\",\n  \"output_format\": \"json\",\n  \"max_alternatives\": 2\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"file_id\": \"FILE_ID\",\n  \"output_format\": \"json\",\n  \"enable_word_timestamps\": true,\n  \"remove_filler_words\": false\n}\n```\n\n#### Actions\n\n- `transcribe_quick`: audio up to 15 minutes. Price: 100 credits.\n- `transcribe_standard`: audio up to 30 minutes. Price: 150 credits.\n- `transcribe_extended`: audio up to 60 minutes. Price: 200 credits.\n\n#### Notes\n\n- Provide either `file_id` or `public_url`.\n- `public_url` must be an HTTPS URL and cannot point to private or internal network addresses.\n- If `language_code` is omitted, the tool defaults to `en-US`.\n- Supported output formats: `text`, `srt`, `vtt`, `json`.\n- Optional controls: `enable_diarization`, `enable_word_timestamps`, `remove_filler_words`, `enable_profanity_filter`, `max_alternatives`.\n- `remove_filler_words` defaults to `true`, which uses Google STT V2's cleaned transcript path.\n- Set `remove_filler_words` to `false` to preserve disfluencies through Vercel AI Gateway using the `openai/whisper-1` gateway model slug. This path always requests word-level timestamps from the gateway for clipping workflows.\n- `remove_filler_words=false` does not support `enable_diarization=true` or `max_alternatives` greater than `1`; use the default cleaned path for those features.\n- Every successful transcription returns the selected output inline through `text`, `srt_content`, `vtt_content`, or `json_data`.\n- During invocations with File Manager storage available, `text` and `json` results are stored for every successful transcription; `srt` and `vtt` results are stored when the generated subtitle content is non-empty. The corresponding filenames are `transcription.txt`, `transcription.json`, `transcription.srt`, and `transcription.vtt`.\n- Stored artifacts are returned through the existing `result_file_id` and `result_signed_url` fields. Agents should use `result_file_id` for later File Manager operations.\n- If transcription succeeds but artifact storage fails, the inline result remains available and `result_file_error` explains that the File Manager file could not be created.\n\n## When To Use\n- Use this skill for `Speech to Text With Speakers` on AgentPMT.\n- Use it when an agent needs this specific tool's behavior, schema, inputs, outputs, and invocation shape.\n- Search and activation keywords: speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, transcribe extended, file id, public url.\n- Supported action names: `transcribe_extended`, `transcribe_quick`, `transcribe_standard`.\n\n## Use Cases\n- Transcribe meeting recordings\n- Generate subtitles and captions for videos\n- Convert voice memos to searchable text\n- Transcribe podcast episodes\n- Create interview transcripts with speaker labels\n- Produce SRT or WebVTT subtitle files\n- Build searchable audio archives\n- Transcribe webinars and lectures\n- Analyze customer call recordings\n- Content repurposing from audio to text\n\n## Related Product Skills\n- File Management: ../file-management (ClawHub: `file-management`, page: https://clawhub.ai/agentpmt/file-management; skills.sh: `npx skills add AgentPMT/agent-skills --skill file-management`)\n\n## Categories And Industries\nNo categories or industry tags are published for this tool.\n\n## Actions And Schema\nComplete generated action schema: `./schema.md`.\nSupported action count: `3`.\nx402 availability: not enabled for this product.\n\n- `transcribe_extended` (action slug: `transcribe-extended`): Transcribe audio up to 60 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact. Price: `200` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_quick` (action slug: `transcribe-quick`): Transcribe audio up to 15 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact. Price: `100` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_standard` (action slug: `transcribe-standard`): Transcribe audio up to 30 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact. Price: `150` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n\n## Live Schema And Examples\nUse the compact schema above for ordinary calls. Before a new production integration, or whenever parameters, enum values, nested objects, outputs, or examples are unclear, fetch live details first.\n\n- Exact schema: call `agentpmt-tool-search-and-execution` with `action: \"get_schema\"`, and `tool_id: \"speech-to-text-with-speakers\"`.\n- Detailed examples: call `agentpmt-tool-search-and-execution` with `action: \"get_instructions\"` and `tool_id: \"speech-to-text-with-speakers\"`, or call this product with `action: \"get_instructions\"` when the product tool is already selected.\n- Treat returned live schema and instructions as more specific than this generated summary.\n\nMCP schema lookup through the main AgentPMT MCP server:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"AgentPMT-Tool-Search-and-Execution\",\n    \"arguments\": {\n      \"action\": \"get_schema\",\n      \"tool_id\": \"speech-to-text-with-speakers\"\n    }\n  }\n}\n```\n\nFor live examples, keep the same MCP tool and use these arguments:\n\n```json\n{\n  \"action\": \"get_instructions\",\n  \"tool_id\": \"speech-to-text-with-speakers\"\n}\n```\n\nAuthenticated AgentPMT REST schema lookup body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_schema\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\nAuthenticated AgentPMT REST live examples body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_instructions\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\n## Call This Tool\nProduct slug: `speech-to-text-with-speakers`\n\nMarketplace page: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n\n- AgentPMT account route: first use `../agentpmt-account-mcp-rest-api-setup` to connect the main MCP server or REST API for an Agent Group where this tool is enabled.\n- x402 route: not enabled for this product.\n- AgentPMT overview: use `../what-is-agentpmt` for marketplace, Agent Group, workflow, MCP, REST, and payment concepts.\n\nIf those setup skills are not installed beside this product skill, use the downloads below.\n\nCore AgentPMT setup skills:\n- What AgentPMT is: ../what-is-agentpmt\n  - ClawHub page: https://clawhub.ai/agentpmt/what-is-agentpmt\n  - OpenClaw install: `openclaw skills install what-is-agentpmt`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup\n  - ClawHub page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup\n  - OpenClaw install: `openclaw skills install agentpmt-account-mcp-rest-api-setup`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`\n\nskills.sh install script:\n\n```bash\nnpx skills add AgentPMT/agent-skills --skill what-is-agentpmt\nnpx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup\n```\n\nMCP call shape after the main AgentPMT MCP server is connected:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"Speech-to-Text-With-Speakers\",\n    \"arguments\": {\n      \"action\": \"transcribe_extended\",\n      \"enable_diarization\": false,\n      \"enable_profanity_filter\": false,\n      \"enable_word_timestamps\": false,\n      \"file_id\": \"example file id\",\n      \"language_code\": \"example language code\",\n      \"max_alternatives\": 1,\n      \"output_format\": \"text\",\n      \"public_url\": \"https://example.com\"\n    }\n  }\n}\n```\n\nUse the exact tool name returned by `tools/list`; the name above is the expected readable form.\n\nAuthenticated AgentPMT REST call body:\n\n```json\n{\n  \"name\": \"speech-to-text-with-speakers\",\n  \"parameters\": {\n    \"action\": \"transcribe_extended\",\n    \"enable_diarization\": false,\n    \"enable_profanity_filter\": false,\n    \"enable_word_timestamps\": false,\n    \"file_id\": \"example file id\",\n    \"language_code\": \"example language code\",\n    \"max_alternatives\": 1,\n    \"output_format\": \"text\",\n    \"public_url\": \"https://example.com\"\n  }\n}\n```\n\nUse the setup skill for the account connection details before making REST calls.\n\n## Response Handling\n- Treat the returned JSON as the source of truth for this tool call.\n- If the response includes warnings or correction targets, apply them before retrying.\n- If the response includes a `passed` or success-style boolean, use it as the workflow gate.\n- If validation fails or the response shape is unclear, call `get_schema` or `get_instructions` before retrying.\n- If `transcribe_extended` fails, preserve the request parameters and retry only after fixing schema, auth, or payment errors.\n\n## Security\n- Do not place account secrets, wallet private keys, mnemonics, signatures, or payment headers in prompts or logs.\n- Keep tool inputs scoped to the minimum content needed for the task.\n- Use the setup skills for credential handling; this product skill only defines product-specific behavior.\n\n## AgentPMT Reference\n- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)\n- Marketplace product: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n- AgentPMT main MCP server: https://api.agentpmt.com/mcp/\n- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase\n\nFile v1.0.5:_meta.json\n\n{\n  \"ownerId\": \"kn798pfbxm62kkd2750t7vsex5819pyc\",\n  \"slug\": \"speech-to-text-with-speakers\",\n  \"version\": \"1.0.5\",\n  \"publishedAt\": 1784642649319\n}\n\nFile v1.0.5:schema.md\n\n# Speech to Text With Speakers Schema\n\nThis generated reference belongs to the adjacent `SKILL.md`. Use it for exact action names, action slugs, parameter summaries, sample parameters, and generated JSON parameter schemas.\n\nProduct slug: `speech-to-text-with-speakers`\n\nx402 availability: not enabled for this product.\n\n## `transcribe_extended`\n\nAction slug: `transcribe-extended`\n\nPrice: `200` credits\n\nTranscribe audio up to 60 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_quick`\n\nAction slug: `transcribe-quick`\n\nPrice: `100` credits\n\nTranscribe audio up to 15 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_standard`\n\nAction slug: `transcribe-standard`\n\nPrice: `150` credits\n\nTranscribe audio up to 30 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\nFile v1.0.5:skill-card.md\n\n## Description: <br>\nTranscribes audio from a File Manager file ID or HTTPS URL into text, SRT, WebVTT, or JSON with optional speaker diarization, word timestamps, profanity filtering, and tiered limits up to 60 minutes. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[agentpmt](https://clawhub.ai/user/agentpmt) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal agents and developers use this skill to send recordings from AgentPMT File Manager IDs or HTTPS URLs to AgentPMT-hosted transcription actions and receive transcripts, subtitles, or timestamped JSON for meetings, media, interviews, podcasts, and archives. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Recordings, derived transcripts, and transcript artifacts may be sent to AgentPMT-hosted transcription services and stored as File Manager artifacts. <br>\nMitigation: Use the skill only when organizational policy permits that data handling, and avoid confidential, regulated, or consent-sensitive recordings unless artifact access and retention are managed. <br>\nRisk: Stored transcription outputs can expose sensitive audio-derived content beyond the immediate inline response. <br>\nMitigation: Prefer File Manager artifact IDs for controlled follow-up operations and review artifact permissions, retention, and sharing before processing sensitive recordings. <br>\n\n\n## Reference(s): <br>\n- [AgentPMT marketplace listing](https://www.agentpmt.com/marketplace/speech-to-text-with-speakers) <br>\n- [ClawHub skill page](https://clawhub.ai/agentpmt/skills/speech-to-text-with-speakers) <br>\n- [Action schema](artifact/schema.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, JSON, configuration, guidance] <br>\n**Output Format:** [Inline tool-call JSON containing text, SRT/WebVTT subtitle content, or structured transcription data, with File Manager artifact IDs and signed URLs when storage is available.] <br>\n**Output Parameters:** [1D; action plus file_id or public_url, output_format, language_code, diarization, timestamp, profanity, filler-word, max_alternatives, and tier-specific duration controls.] <br>\n**Other Properties Related to Output:** [AgentPMT-hosted remote calls; public_url inputs must be HTTPS and cannot point to private or internal network addresses.] <br>\n\n## Skill Version(s): <br>\n1.0.5 (source: server release and SKILL.md frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.4: 4 files, 6962 bytes\n\nFiles: schema.md (12079b), skill-card.md (2529b), SKILL.md (12668b), _meta.json (147b)\n\nFile v1.0.4:SKILL.md\n\n---\nname: speech-to-text-with-speakers\ndescription: \"Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an agent needs speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, transcribe extended, file id, public url through AgentPMT-hosted remote tool calls. Discovery terms: speech to text with speakers.\"\nversion: 1.0.4\nhomepage: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\ncompatibility: \"Agent instructions for AgentPMT-hosted remote tool calls. Follow this skill body for supported account, wallet, and setup routes. No local command runtime is declared.\"\nmetadata: {\"author\":\"agentpmt\",\"openclaw\":{\"homepage\":\"https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\"}}\n---\n# Speech to Text With Speakers\n\n## Freshness\nLast updated: `2026-07-21`.\n\nIf the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.\n\n## What This Tool Does\nTurn any audio recording into clean, searchable text in seconds. Transcribe voice memos, meetings, interviews, podcasts, and webinars with accurate speech recognition that handles accents and background noise. Get plain text for quick reference, SRT or WebVTT subtitles for video captioning, or rich JSON output with word-level timestamps and speaker identification. Choose from three tiers based on recording length — up to 15, 30, or 60 minutes — and optionally enable speaker diarization to label who said what, profanity filtering, and alternative transcripts for maximum accuracy.\n\n## Product Instructions\n### Speech to Text\n\nTranscribe audio with one tool and choose the action that matches the upload length.\n\n#### Tool Call Format\n\n```json\n{\n  \"action\": \"get_instructions\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_quick\",\n  \"file_id\": \"FILE_ID\",\n  \"language_code\": \"en-US\",\n  \"output_format\": \"text\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"public_url\": \"https://example.com/meeting.m4a\",\n  \"output_format\": \"vtt\",\n  \"enable_word_timestamps\": true,\n  \"enable_diarization\": true\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_extended\",\n  \"public_url\": \"https://example.com/interview.webm\",\n  \"output_format\": \"json\",\n  \"max_alternatives\": 2\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"file_id\": \"FILE_ID\",\n  \"output_format\": \"json\",\n  \"enable_word_timestamps\": true,\n  \"remove_filler_words\": false\n}\n```\n\n#### Actions\n\n- `transcribe_quick`: audio up to 15 minutes. Price: 100 credits.\n- `transcribe_standard`: audio up to 30 minutes. Price: 150 credits.\n- `transcribe_extended`: audio up to 60 minutes. Price: 200 credits.\n\n#### Notes\n\n- Provide either `file_id` or `public_url`.\n- `public_url` must be an HTTPS URL and cannot point to private or internal network addresses.\n- If `language_code` is omitted, the tool defaults to `en-US`.\n- Supported output formats: `text`, `srt`, `vtt`, `json`.\n- Optional controls: `enable_diarization`, `enable_word_timestamps`, `remove_filler_words`, `enable_profanity_filter`, `max_alternatives`.\n- `remove_filler_words` defaults to `true`, which uses Google STT V2's cleaned transcript path.\n- Set `remove_filler_words` to `false` to preserve disfluencies through Vercel AI Gateway using the `openai/whisper-1` gateway model slug. This path always requests word-level timestamps from the gateway for clipping workflows.\n- `remove_filler_words=false` does not support `enable_diarization=true` or `max_alternatives` greater than `1`; use the default cleaned path for those features.\n- Every successful transcription returns the selected output inline and as a File Manager artifact: `text` returns `text` plus `transcription.txt`; `srt` returns `srt_content` plus `transcription.srt`; `vtt` returns `vtt_content` plus `transcription.vtt`; and `json` returns `json_data` plus `transcription.json`.\n- File artifacts are returned through the existing `result_file_id` and `result_signed_url` fields. Agents should use `result_file_id` for later File Manager operations.\n- If transcription succeeds but artifact storage fails, the inline result remains available and `result_file_error` explains that the File Manager file could not be created.\n\n## When To Use\n- Use this skill for `Speech to Text With Speakers` on AgentPMT.\n- Use it when an agent needs this specific tool's behavior, schema, inputs, outputs, and invocation shape.\n- Search and activation keywords: speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, transcribe extended, file id, public url.\n- Supported action names: `transcribe_extended`, `transcribe_quick`, `transcribe_standard`.\n\n## Use Cases\n- Transcribe meeting recordings\n- Generate subtitles and captions for videos\n- Convert voice memos to searchable text\n- Transcribe podcast episodes\n- Create interview transcripts with speaker labels\n- Produce SRT or WebVTT subtitle files\n- Build searchable audio archives\n- Transcribe webinars and lectures\n- Analyze customer call recordings\n- Content repurposing from audio to text\n\n## Related Product Skills\n- File Management: ../file-management (ClawHub: `file-management`, page: https://clawhub.ai/agentpmt/file-management; skills.sh: `npx skills add AgentPMT/agent-skills --skill file-management`)\n\n## Categories And Industries\nNo categories or industry tags are published for this tool.\n\n## Actions And Schema\nComplete generated action schema: `./schema.md`.\nSupported action count: `3`.\nx402 availability: not enabled for this product.\n\n- `transcribe_extended` (action slug: `transcribe-extended`): Transcribe audio up to 60 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact. Price: `200` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_quick` (action slug: `transcribe-quick`): Transcribe audio up to 15 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact. Price: `100` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_standard` (action slug: `transcribe-standard`): Transcribe audio up to 30 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact. Price: `150` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n\n## Live Schema And Examples\nUse the compact schema above for ordinary calls. Before a new production integration, or whenever parameters, enum values, nested objects, outputs, or examples are unclear, fetch live details first.\n\n- Exact schema: call `agentpmt-tool-search-and-execution` with `action: \"get_schema\"`, and `tool_id: \"speech-to-text-with-speakers\"`.\n- Detailed examples: call `agentpmt-tool-search-and-execution` with `action: \"get_instructions\"` and `tool_id: \"speech-to-text-with-speakers\"`, or call this product with `action: \"get_instructions\"` when the product tool is already selected.\n- Treat returned live schema and instructions as more specific than this generated summary.\n\nMCP schema lookup through the main AgentPMT MCP server:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"AgentPMT-Tool-Search-and-Execution\",\n    \"arguments\": {\n      \"action\": \"get_schema\",\n      \"tool_id\": \"speech-to-text-with-speakers\"\n    }\n  }\n}\n```\n\nFor live examples, keep the same MCP tool and use these arguments:\n\n```json\n{\n  \"action\": \"get_instructions\",\n  \"tool_id\": \"speech-to-text-with-speakers\"\n}\n```\n\nAuthenticated AgentPMT REST schema lookup body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_schema\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\nAuthenticated AgentPMT REST live examples body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_instructions\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\n## Call This Tool\nProduct slug: `speech-to-text-with-speakers`\n\nMarketplace page: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n\n- AgentPMT account route: first use `../agentpmt-account-mcp-rest-api-setup` to connect the main MCP server or REST API for an Agent Group where this tool is enabled.\n- x402 route: not enabled for this product.\n- AgentPMT overview: use `../what-is-agentpmt` for marketplace, Agent Group, workflow, MCP, REST, and payment concepts.\n\nIf those setup skills are not installed beside this product skill, use the downloads below.\n\nCore AgentPMT setup skills:\n- What AgentPMT is: ../what-is-agentpmt\n  - ClawHub page: https://clawhub.ai/agentpmt/what-is-agentpmt\n  - OpenClaw install: `openclaw skills install what-is-agentpmt`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup\n  - ClawHub page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup\n  - OpenClaw install: `openclaw skills install agentpmt-account-mcp-rest-api-setup`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`\n\nskills.sh install script:\n\n```bash\nnpx skills add AgentPMT/agent-skills --skill what-is-agentpmt\nnpx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup\n```\n\nMCP call shape after the main AgentPMT MCP server is connected:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"Speech-to-Text-With-Speakers\",\n    \"arguments\": {\n      \"action\": \"transcribe_extended\",\n      \"enable_diarization\": false,\n      \"enable_profanity_filter\": false,\n      \"enable_word_timestamps\": false,\n      \"file_id\": \"example file id\",\n      \"language_code\": \"example language code\",\n      \"max_alternatives\": 1,\n      \"output_format\": \"text\",\n      \"public_url\": \"https://example.com\"\n    }\n  }\n}\n```\n\nUse the exact tool name returned by `tools/list`; the name above is the expected readable form.\n\nAuthenticated AgentPMT REST call body:\n\n```json\n{\n  \"name\": \"speech-to-text-with-speakers\",\n  \"parameters\": {\n    \"action\": \"transcribe_extended\",\n    \"enable_diarization\": false,\n    \"enable_profanity_filter\": false,\n    \"enable_word_timestamps\": false,\n    \"file_id\": \"example file id\",\n    \"language_code\": \"example language code\",\n    \"max_alternatives\": 1,\n    \"output_format\": \"text\",\n    \"public_url\": \"https://example.com\"\n  }\n}\n```\n\nUse the setup skill for the account connection details before making REST calls.\n\n## Response Handling\n- Treat the returned JSON as the source of truth for this tool call.\n- If the response includes warnings or correction targets, apply them before retrying.\n- If the response includes a `passed` or success-style boolean, use it as the workflow gate.\n- If validation fails or the response shape is unclear, call `get_schema` or `get_instructions` before retrying.\n- If `transcribe_extended` fails, preserve the request parameters and retry only after fixing schema, auth, or payment errors.\n\n## Security\n- Do not place account secrets, wallet private keys, mnemonics, signatures, or payment headers in prompts or logs.\n- Keep tool inputs scoped to the minimum content needed for the task.\n- Use the setup skills for credential handling; this product skill only defines product-specific behavior.\n\n## AgentPMT Reference\n- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)\n- Marketplace product: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n- AgentPMT main MCP server: https://api.agentpmt.com/mcp/\n- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase\n\nFile v1.0.4:_meta.json\n\n{\n  \"ownerId\": \"kn798pfbxm62kkd2750t7vsex5819pyc\",\n  \"slug\": \"speech-to-text-with-speakers\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1784607217643\n}\n\nFile v1.0.4:schema.md\n\n# Speech to Text With Speakers Schema\n\nThis generated reference belongs to the adjacent `SKILL.md`. Use it for exact action names, action slugs, parameter summaries, sample parameters, and generated JSON parameter schemas.\n\nProduct slug: `speech-to-text-with-speakers`\n\nx402 availability: not enabled for this product.\n\n## `transcribe_extended`\n\nAction slug: `transcribe-extended`\n\nPrice: `200` credits\n\nTranscribe audio up to 60 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_quick`\n\nAction slug: `transcribe-quick`\n\nPrice: `100` credits\n\nTranscribe audio up to 15 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_standard`\n\nAction slug: `transcribe-standard`\n\nPrice: `150` credits\n\nTranscribe audio up to 30 minutes. Returns the selected content inline with result_file_id and result_signed_url for the File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. Successful results include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\nFile v1.0.4:skill-card.md\n\n## Description: <br>\nTranscribes audio from a file ID or public HTTPS URL into text, SRT, WebVTT, or JSON with optional speaker diarization, word timestamps, profanity filtering, and alternative transcripts. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[agentpmt](https://clawhub.ai/user/agentpmt) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and developers use this skill to transcribe meetings, interviews, podcasts, voice memos, webinars, and videos into searchable transcripts or caption files. It supports short, standard, and extended recordings up to 60 minutes. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Selected audio files or public audio URLs and resulting transcripts are processed and stored through AgentPMT-related services. <br>\nMitigation: Submit only recordings allowed by the user's account setup and data-handling obligations; avoid confidential, regulated, or third-party recordings unless approved. <br>\nRisk: Public URL inputs may expose unintended audio if links are broad, shared, or point to the wrong asset. <br>\nMitigation: Use HTTPS URLs scoped to the intended audio file and avoid private or internal network resources. <br>\n\n\n## Reference(s): <br>\n- [AgentPMT Marketplace Product](https://www.agentpmt.com/marketplace/speech-to-text-with-speakers) <br>\n- [ClawHub Skill Page](https://clawhub.ai/agentpmt/skills/speech-to-text-with-speakers) <br>\n- [Generated Action Schema](artifact/schema.md) <br>\n- [AgentPMT Account MCP/REST Setup](https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup) <br>\n- [AgentPMT File Management](https://clawhub.ai/agentpmt/file-management) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, JSON, Files, Guidance] <br>\n**Output Format:** [Plain text, SRT, WebVTT, or JSON with optional File Manager artifact references] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Supports 15, 30, and 60 minute transcription tiers with optional diarization, word timestamps, profanity filtering, and alternative transcripts.] <br>\n\n## Skill Version(s): <br>\n1.0.4 (source: release evidence and SKILL.md frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.3: 4 files, 6896 bytes\n\nFiles: schema.md (11767b), skill-card.md (2488b), SKILL.md (12334b), _meta.json (147b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: speech-to-text-with-speakers\ndescription: \"Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an agent needs speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, transcribe extended, file id, public url through AgentPMT-hosted remote tool calls. Discovery terms: speech to text with speakers.\"\nversion: 1.0.3\nhomepage: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\ncompatibility: \"Agent instructions for AgentPMT-hosted remote tool calls. Follow this skill body for supported account, wallet, and setup routes. No local command runtime is declared.\"\nmetadata: {\"author\":\"agentpmt\",\"openclaw\":{\"homepage\":\"https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\"}}\n---\n# Speech to Text With Speakers\n\n## Freshness\nLast updated: `2026-07-21`.\n\nIf the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.\n\n## What This Tool Does\nTurn any audio recording into clean, searchable text in seconds. Transcribe voice memos, meetings, interviews, podcasts, and webinars with accurate speech recognition that handles accents and background noise. Get plain text for quick reference, SRT or WebVTT subtitles for video captioning, or rich JSON output with word-level timestamps and speaker identification. Choose from three tiers based on recording length — up to 15, 30, or 60 minutes — and optionally enable speaker diarization to label who said what, profanity filtering, and alternative transcripts for maximum accuracy.\n\n## Product Instructions\n### Speech to Text\n\nTranscribe audio with one tool and choose the action that matches the upload length.\n\n#### Tool Call Format\n\n```json\n{\n  \"action\": \"get_instructions\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_quick\",\n  \"file_id\": \"FILE_ID\",\n  \"language_code\": \"en-US\",\n  \"output_format\": \"text\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"public_url\": \"https://example.com/meeting.m4a\",\n  \"output_format\": \"vtt\",\n  \"enable_word_timestamps\": true,\n  \"enable_diarization\": true\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_extended\",\n  \"public_url\": \"https://example.com/interview.webm\",\n  \"output_format\": \"json\",\n  \"max_alternatives\": 2\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"file_id\": \"FILE_ID\",\n  \"output_format\": \"json\",\n  \"enable_word_timestamps\": true,\n  \"remove_filler_words\": false\n}\n```\n\n#### Actions\n\n- `transcribe_quick`: audio up to 15 minutes. Price: 100 credits.\n- `transcribe_standard`: audio up to 30 minutes. Price: 150 credits.\n- `transcribe_extended`: audio up to 60 minutes. Price: 200 credits.\n\n#### Notes\n\n- Provide either `file_id` or `public_url`.\n- `public_url` must be an HTTPS URL and cannot point to private or internal network addresses.\n- If `language_code` is omitted, the tool defaults to `en-US`.\n- Supported output formats: `text`, `srt`, `vtt`, `json`.\n- Optional controls: `enable_diarization`, `enable_word_timestamps`, `remove_filler_words`, `enable_profanity_filter`, `max_alternatives`.\n- `remove_filler_words` defaults to `true`, which uses Google STT V2's cleaned transcript path.\n- Set `remove_filler_words` to `false` to preserve disfluencies through Vercel AI Gateway using the `openai/whisper-1` gateway model slug. This path always requests word-level timestamps from the gateway for clipping workflows.\n- `remove_filler_words=false` does not support `enable_diarization=true` or `max_alternatives` greater than `1`; use the default cleaned path for those features.\n- Every successful transcription returns the selected output both inline and as a File Manager file during normal platform invocations: `text` uses `text` plus `transcription.txt`; `srt` uses `srt_content` plus `transcription.srt`; `vtt` uses `vtt_content` plus `transcription.vtt`; and `json` uses `json_data` plus `transcription.json`. Use `result_file_id` for later File Manager operations and `result_signed_url` for direct download.\n\n## When To Use\n- Use this skill for `Speech to Text With Speakers` on AgentPMT.\n- Use it when an agent needs this specific tool's behavior, schema, inputs, outputs, and invocation shape.\n- Search and activation keywords: speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, transcribe extended, file id, public url.\n- Supported action names: `transcribe_extended`, `transcribe_quick`, `transcribe_standard`.\n\n## Use Cases\n- Transcribe meeting recordings\n- Generate subtitles and captions for videos\n- Convert voice memos to searchable text\n- Transcribe podcast episodes\n- Create interview transcripts with speaker labels\n- Produce SRT or WebVTT subtitle files\n- Build searchable audio archives\n- Transcribe webinars and lectures\n- Analyze customer call recordings\n- Content repurposing from audio to text\n\n## Related Product Skills\n- File Management: ../file-management (ClawHub: `file-management`, page: https://clawhub.ai/agentpmt/file-management; skills.sh: `npx skills add AgentPMT/agent-skills --skill file-management`)\n\n## Categories And Industries\nNo categories or industry tags are published for this tool.\n\n## Actions And Schema\nComplete generated action schema: `./schema.md`.\nSupported action count: `3`.\nx402 availability: not enabled for this product.\n\n- `transcribe_extended` (action slug: `transcribe-extended`): Transcribe audio up to 60 minutes. Returns the requested transcription inline and as a File Manager file. Price: `200` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_quick` (action slug: `transcribe-quick`): Transcribe audio up to 15 minutes. Returns the requested transcription inline and as a File Manager file. Price: `100` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_standard` (action slug: `transcribe-standard`): Transcribe audio up to 30 minutes. Returns the requested transcription inline and as a File Manager file. Price: `150` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n\n## Live Schema And Examples\nUse the compact schema above for ordinary calls. Before a new production integration, or whenever parameters, enum values, nested objects, outputs, or examples are unclear, fetch live details first.\n\n- Exact schema: call `agentpmt-tool-search-and-execution` with `action: \"get_schema\"`, and `tool_id: \"speech-to-text-with-speakers\"`.\n- Detailed examples: call `agentpmt-tool-search-and-execution` with `action: \"get_instructions\"` and `tool_id: \"speech-to-text-with-speakers\"`, or call this product with `action: \"get_instructions\"` when the product tool is already selected.\n- Treat returned live schema and instructions as more specific than this generated summary.\n\nMCP schema lookup through the main AgentPMT MCP server:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"AgentPMT-Tool-Search-and-Execution\",\n    \"arguments\": {\n      \"action\": \"get_schema\",\n      \"tool_id\": \"speech-to-text-with-speakers\"\n    }\n  }\n}\n```\n\nFor live examples, keep the same MCP tool and use these arguments:\n\n```json\n{\n  \"action\": \"get_instructions\",\n  \"tool_id\": \"speech-to-text-with-speakers\"\n}\n```\n\nAuthenticated AgentPMT REST schema lookup body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_schema\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\nAuthenticated AgentPMT REST live examples body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_instructions\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\n## Call This Tool\nProduct slug: `speech-to-text-with-speakers`\n\nMarketplace page: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n\n- AgentPMT account route: first use `../agentpmt-account-mcp-rest-api-setup` to connect the main MCP server or REST API for an Agent Group where this tool is enabled.\n- x402 route: not enabled for this product.\n- AgentPMT overview: use `../what-is-agentpmt` for marketplace, Agent Group, workflow, MCP, REST, and payment concepts.\n\nIf those setup skills are not installed beside this product skill, use the downloads below.\n\nCore AgentPMT setup skills:\n- What AgentPMT is: ../what-is-agentpmt\n  - ClawHub page: https://clawhub.ai/agentpmt/what-is-agentpmt\n  - OpenClaw install: `openclaw skills install what-is-agentpmt`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup\n  - ClawHub page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup\n  - OpenClaw install: `openclaw skills install agentpmt-account-mcp-rest-api-setup`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`\n\nskills.sh install script:\n\n```bash\nnpx skills add AgentPMT/agent-skills --skill what-is-agentpmt\nnpx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup\n```\n\nMCP call shape after the main AgentPMT MCP server is connected:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"Speech-to-Text-With-Speakers\",\n    \"arguments\": {\n      \"action\": \"transcribe_extended\",\n      \"enable_diarization\": false,\n      \"enable_profanity_filter\": false,\n      \"enable_word_timestamps\": false,\n      \"file_id\": \"example file id\",\n      \"language_code\": \"example language code\",\n      \"max_alternatives\": 1,\n      \"output_format\": \"text\",\n      \"public_url\": \"https://example.com\"\n    }\n  }\n}\n```\n\nUse the exact tool name returned by `tools/list`; the name above is the expected readable form.\n\nAuthenticated AgentPMT REST call body:\n\n```json\n{\n  \"name\": \"speech-to-text-with-speakers\",\n  \"parameters\": {\n    \"action\": \"transcribe_extended\",\n    \"enable_diarization\": false,\n    \"enable_profanity_filter\": false,\n    \"enable_word_timestamps\": false,\n    \"file_id\": \"example file id\",\n    \"language_code\": \"example language code\",\n    \"max_alternatives\": 1,\n    \"output_format\": \"text\",\n    \"public_url\": \"https://example.com\"\n  }\n}\n```\n\nUse the setup skill for the account connection details before making REST calls.\n\n## Response Handling\n- Treat the returned JSON as the source of truth for this tool call.\n- If the response includes warnings or correction targets, apply them before retrying.\n- If the response includes a `passed` or success-style boolean, use it as the workflow gate.\n- If validation fails or the response shape is unclear, call `get_schema` or `get_instructions` before retrying.\n- If `transcribe_extended` fails, preserve the request parameters and retry only after fixing schema, auth, or payment errors.\n\n## Security\n- Do not place account secrets, wallet private keys, mnemonics, signatures, or payment headers in prompts or logs.\n- Keep tool inputs scoped to the minimum content needed for the task.\n- Use the setup skills for credential handling; this product skill only defines product-specific behavior.\n\n## AgentPMT Reference\n- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)\n- Marketplace product: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n- AgentPMT main MCP server: https://api.agentpmt.com/mcp/\n- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn798pfbxm62kkd2750t7vsex5819pyc\",\n  \"slug\": \"speech-to-text-with-speakers\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1784606729851\n}\n\nFile v1.0.3:schema.md\n\n# Speech to Text With Speakers Schema\n\nThis generated reference belongs to the adjacent `SKILL.md`. Use it for exact action names, action slugs, parameter summaries, sample parameters, and generated JSON parameter schemas.\n\nProduct slug: `speech-to-text-with-speakers`\n\nx402 availability: not enabled for this product.\n\n## `transcribe_extended`\n\nAction slug: `transcribe-extended`\n\nPrice: `200` credits\n\nTranscribe audio up to 60 minutes. Returns the requested transcription inline and as a File Manager file.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. The selected result is returned inline and as a File Manager file: .txt, .srt, .vtt, or .json. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. The selected result is returned inline and as a File Manager file: .txt, .srt, .vtt, or .json.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_quick`\n\nAction slug: `transcribe-quick`\n\nPrice: `100` credits\n\nTranscribe audio up to 15 minutes. Returns the requested transcription inline and as a File Manager file.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. The selected result is returned inline and as a File Manager file: .txt, .srt, .vtt, or .json. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. The selected result is returned inline and as a File Manager file: .txt, .srt, .vtt, or .json.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_standard`\n\nAction slug: `transcribe-standard`\n\nPrice: `150` credits\n\nTranscribe audio up to 30 minutes. Returns the requested transcription inline and as a File Manager file.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. The selected result is returned inline and as a File Manager file: .txt, .srt, .vtt, or .json. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result. The selected result is returned inline and as a File Manager file: .txt, .srt, .vtt, or .json.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\nFile v1.0.3:skill-card.md\n\n## Description: <br>\nTranscribes audio from a file ID or HTTPS public URL into text, SRT, WebVTT, or JSON with optional speaker diarization, word timestamps, profanity filtering, and alternate transcripts for recordings up to 60 minutes. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[agentpmt](https://clawhub.ai/user/agentpmt) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal agents and developers use this skill to transcribe meetings, voice memos, interviews, podcasts, webinars, and videos into searchable text, captions, subtitles, or structured JSON. It is intended for AgentPMT-hosted transcription calls where the caller selects a short, standard, or extended duration tier. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Selected audio and generated transcripts are handled by AgentPMT-hosted transcription services and saved as File Manager files. <br>\nMitigation: Use the skill only with recordings you are authorized to process, avoid confidential or regulated content unless retention and deletion options are understood, and review File Manager storage expectations before use. <br>\nRisk: Transcription accuracy can be affected when the language is omitted or when audio is accuracy-sensitive. <br>\nMitigation: Set language_code explicitly for non-English or accuracy-sensitive audio and review the transcript before relying on it. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/agentpmt/skills/speech-to-text-with-speakers) <br>\n- [AgentPMT Marketplace Page](https://www.agentpmt.com/marketplace/speech-to-text-with-speakers) <br>\n- [Generated Action Schema](artifact/schema.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, configuration, guidance] <br>\n**Output Format:** [Plain text, SRT, WebVTT, or JSON returned inline and as a File Manager file] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Outputs may include result_file_id and result_signed_url for later file operations or download.] <br>\n\n## Skill Version(s): <br>\n1.0.3 (source: server release evidence and SKILL.md frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.2: 4 files, 6853 bytes\n\nFiles: schema.md (10984b), skill-card.md (2918b), SKILL.md (11811b), _meta.json (147b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: speech-to-text-with-speakers\ndescription: \"Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an agent needs speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, transcribe extended, file id, public url through AgentPMT-hosted remote tool calls. Discovery terms: speech to text with speakers.\"\nversion: 1.0.2\nhomepage: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\ncompatibility: \"Agent instructions for AgentPMT-hosted remote tool calls. Follow this skill body for supported account, wallet, and setup routes. No local command runtime is declared.\"\nmetadata: {\"author\":\"agentpmt\",\"openclaw\":{\"homepage\":\"https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\"}}\n---\n# Speech to Text With Speakers\n\n## Freshness\nLast updated: `2026-07-21`.\n\nIf the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.\n\n## What This Tool Does\nTurn any audio recording into clean, searchable text in seconds. Transcribe voice memos, meetings, interviews, podcasts, and webinars with accurate speech recognition that handles accents and background noise. Get plain text for quick reference, SRT or WebVTT subtitles for video captioning, or rich JSON output with word-level timestamps and speaker identification. Choose from three tiers based on recording length — up to 15, 30, or 60 minutes — and optionally enable speaker diarization to label who said what, profanity filtering, and alternative transcripts for maximum accuracy.\n\n## Product Instructions\n### Speech to Text\n\nTranscribe audio with one tool and choose the action that matches the upload length.\n\n#### Tool Call Format\n\n```json\n{\n  \"action\": \"get_instructions\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_quick\",\n  \"file_id\": \"FILE_ID\",\n  \"language_code\": \"en-US\",\n  \"output_format\": \"text\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"public_url\": \"https://example.com/meeting.m4a\",\n  \"output_format\": \"vtt\",\n  \"enable_word_timestamps\": true,\n  \"enable_diarization\": true\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_extended\",\n  \"public_url\": \"https://example.com/interview.webm\",\n  \"output_format\": \"json\",\n  \"max_alternatives\": 2\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"file_id\": \"FILE_ID\",\n  \"output_format\": \"json\",\n  \"enable_word_timestamps\": true,\n  \"remove_filler_words\": false\n}\n```\n\n#### Actions\n\n- `transcribe_quick`: audio up to 15 minutes. Price: 100 credits.\n- `transcribe_standard`: audio up to 30 minutes. Price: 150 credits.\n- `transcribe_extended`: audio up to 60 minutes. Price: 200 credits.\n\n#### Notes\n\n- Provide either `file_id` or `public_url`.\n- `public_url` must be an HTTPS URL and cannot point to private or internal network addresses.\n- If `language_code` is omitted, the tool defaults to `en-US`.\n- Supported output formats: `text`, `srt`, `vtt`, `json`.\n- Optional controls: `enable_diarization`, `enable_word_timestamps`, `remove_filler_words`, `enable_profanity_filter`, `max_alternatives`.\n- `remove_filler_words` defaults to `true`, which uses Google STT V2's cleaned transcript path.\n- Set `remove_filler_words` to `false` to preserve disfluencies through Vercel AI Gateway using the `openai/whisper-1` gateway model slug. This path always requests word-level timestamps from the gateway for clipping workflows.\n- `remove_filler_words=false` does not support `enable_diarization=true` or `max_alternatives` greater than `1`; use the default cleaned path for those features.\n- Subtitle responses include inline subtitle content and may also include stored file links during normal platform invocations.\n\n## When To Use\n- Use this skill for `Speech to Text With Speakers` on AgentPMT.\n- Use it when an agent needs this specific tool's behavior, schema, inputs, outputs, and invocation shape.\n- Search and activation keywords: speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, transcribe extended, file id, public url.\n- Supported action names: `transcribe_extended`, `transcribe_quick`, `transcribe_standard`.\n\n## Use Cases\n- Transcribe meeting recordings\n- Generate subtitles and captions for videos\n- Convert voice memos to searchable text\n- Transcribe podcast episodes\n- Create interview transcripts with speaker labels\n- Produce SRT or WebVTT subtitle files\n- Build searchable audio archives\n- Transcribe webinars and lectures\n- Analyze customer call recordings\n- Content repurposing from audio to text\n\n## Related Product Skills\n- File Management: ../file-management (ClawHub: `file-management`, page: https://clawhub.ai/agentpmt/file-management; skills.sh: `npx skills add AgentPMT/agent-skills --skill file-management`)\n\n## Categories And Industries\nNo categories or industry tags are published for this tool.\n\n## Actions And Schema\nComplete generated action schema: `./schema.md`.\nSupported action count: `3`.\nx402 availability: not enabled for this product.\n\n- `transcribe_extended` (action slug: `transcribe-extended`): Transcribe audio up to 60 minutes. Price: `200` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_quick` (action slug: `transcribe-quick`): Transcribe audio up to 15 minutes. Price: `100` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n- `transcribe_standard` (action slug: `transcribe-standard`): Transcribe audio up to 30 minutes. Price: `150` credits. Parameters: `enable_diarization`, `enable_profanity_filter`, `enable_word_timestamps`, `file_id`, `language_code`, `max_alternatives`, `output_format`, `public_url`, plus 1 more.\n\n## Live Schema And Examples\nUse the compact schema above for ordinary calls. Before a new production integration, or whenever parameters, enum values, nested objects, outputs, or examples are unclear, fetch live details first.\n\n- Exact schema: call `agentpmt-tool-search-and-execution` with `action: \"get_schema\"`, and `tool_id: \"speech-to-text-with-speakers\"`.\n- Detailed examples: call `agentpmt-tool-search-and-execution` with `action: \"get_instructions\"` and `tool_id: \"speech-to-text-with-speakers\"`, or call this product with `action: \"get_instructions\"` when the product tool is already selected.\n- Treat returned live schema and instructions as more specific than this generated summary.\n\nMCP schema lookup through the main AgentPMT MCP server:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"AgentPMT-Tool-Search-and-Execution\",\n    \"arguments\": {\n      \"action\": \"get_schema\",\n      \"tool_id\": \"speech-to-text-with-speakers\"\n    }\n  }\n}\n```\n\nFor live examples, keep the same MCP tool and use these arguments:\n\n```json\n{\n  \"action\": \"get_instructions\",\n  \"tool_id\": \"speech-to-text-with-speakers\"\n}\n```\n\nAuthenticated AgentPMT REST schema lookup body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_schema\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\nAuthenticated AgentPMT REST live examples body:\n\n```json\n{\n  \"name\": \"agentpmt-tool-search-and-execution\",\n  \"parameters\": {\n    \"action\": \"get_instructions\",\n    \"tool_id\": \"speech-to-text-with-speakers\"\n  }\n}\n```\n\n## Call This Tool\nProduct slug: `speech-to-text-with-speakers`\n\nMarketplace page: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n\n- AgentPMT account route: first use `../agentpmt-account-mcp-rest-api-setup` to connect the main MCP server or REST API for an Agent Group where this tool is enabled.\n- x402 route: not enabled for this product.\n- AgentPMT overview: use `../what-is-agentpmt` for marketplace, Agent Group, workflow, MCP, REST, and payment concepts.\n\nIf those setup skills are not installed beside this product skill, use the downloads below.\n\nCore AgentPMT setup skills:\n- What AgentPMT is: ../what-is-agentpmt\n  - ClawHub page: https://clawhub.ai/agentpmt/what-is-agentpmt\n  - OpenClaw install: `openclaw skills install what-is-agentpmt`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup\n  - ClawHub page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup\n  - OpenClaw install: `openclaw skills install agentpmt-account-mcp-rest-api-setup`\n  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`\n\nskills.sh install script:\n\n```bash\nnpx skills add AgentPMT/agent-skills --skill what-is-agentpmt\nnpx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup\n```\n\nMCP call shape after the main AgentPMT MCP server is connected:\n\n```json\n{\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"Speech-to-Text-With-Speakers\",\n    \"arguments\": {\n      \"action\": \"transcribe_extended\",\n      \"enable_diarization\": false,\n      \"enable_profanity_filter\": false,\n      \"enable_word_timestamps\": false,\n      \"file_id\": \"example file id\",\n      \"language_code\": \"example language code\",\n      \"max_alternatives\": 1,\n      \"output_format\": \"text\",\n      \"public_url\": \"https://example.com\"\n    }\n  }\n}\n```\n\nUse the exact tool name returned by `tools/list`; the name above is the expected readable form.\n\nAuthenticated AgentPMT REST call body:\n\n```json\n{\n  \"name\": \"speech-to-text-with-speakers\",\n  \"parameters\": {\n    \"action\": \"transcribe_extended\",\n    \"enable_diarization\": false,\n    \"enable_profanity_filter\": false,\n    \"enable_word_timestamps\": false,\n    \"file_id\": \"example file id\",\n    \"language_code\": \"example language code\",\n    \"max_alternatives\": 1,\n    \"output_format\": \"text\",\n    \"public_url\": \"https://example.com\"\n  }\n}\n```\n\nUse the setup skill for the account connection details before making REST calls.\n\n## Response Handling\n- Treat the returned JSON as the source of truth for this tool call.\n- If the response includes warnings or correction targets, apply them before retrying.\n- If the response includes a `passed` or success-style boolean, use it as the workflow gate.\n- If validation fails or the response shape is unclear, call `get_schema` or `get_instructions` before retrying.\n- If `transcribe_extended` fails, preserve the request parameters and retry only after fixing schema, auth, or payment errors.\n\n## Security\n- Do not place account secrets, wallet private keys, mnemonics, signatures, or payment headers in prompts or logs.\n- Keep tool inputs scoped to the minimum content needed for the task.\n- Use the setup skills for credential handling; this product skill only defines product-specific behavior.\n\n## AgentPMT Reference\n- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)\n- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)\n- Marketplace product: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\n- AgentPMT main MCP server: https://api.agentpmt.com/mcp/\n- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn798pfbxm62kkd2750t7vsex5819pyc\",\n  \"slug\": \"speech-to-text-with-speakers\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1784605785733\n}\n\nFile v1.0.2:schema.md\n\n# Speech to Text With Speakers Schema\n\nThis generated reference belongs to the adjacent `SKILL.md`. Use it for exact action names, action slugs, parameter summaries, sample parameters, and generated JSON parameter schemas.\n\nProduct slug: `speech-to-text-with-speakers`\n\nx402 availability: not enabled for this product.\n\n## `transcribe_extended`\n\nAction slug: `transcribe-extended`\n\nPrice: `200` credits\n\nTranscribe audio up to 60 minutes.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_quick`\n\nAction slug: `transcribe-quick`\n\nPrice: `100` credits\n\nTranscribe audio up to 15 minutes.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\n## `transcribe_standard`\n\nAction slug: `transcribe-standard`\n\nPrice: `150` credits\n\nTranscribe audio up to 30 minutes.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1. |\n\nSample parameters:\n\n```json\n{\n  \"enable_diarization\": false,\n  \"enable_profanity_filter\": false,\n  \"enable_word_timestamps\": false,\n  \"file_id\": \"example file id\",\n  \"language_code\": \"example language code\",\n  \"max_alternatives\": 1,\n  \"output_format\": \"text\",\n  \"public_url\": \"https://example.com\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"enable_diarization\": {\n    \"default\": false,\n    \"description\": \"Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_profanity_filter\": {\n    \"default\": false,\n    \"description\": \"Mask profanity in the returned transcript.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"enable_word_timestamps\": {\n    \"default\": false,\n    \"description\": \"Include word-level timing data in the output.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  },\n  \"file_id\": {\n    \"description\": \"File ID from a prior upload. Provide either file_id or public_url.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"language_code\": {\n    \"description\": \"Optional BCP-47 language code such as en-US; defaults to en-US if omitted.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"max_alternatives\": {\n    \"default\": 1,\n    \"description\": \"Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false.\",\n    \"maximum\": 5,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  },\n  \"output_format\": {\n    \"default\": \"text\",\n    \"description\": \"Output format for the transcription result.\",\n    \"enum\": [\n      \"text\",\n      \"srt\",\n      \"vtt\",\n      \"json\"\n    ],\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"public_url\": {\n    \"description\": \"HTTPS URL to a downloadable audio file. Provide either public_url or file_id.\",\n    \"required\": false,\n    \"type\": \"string\"\n  },\n  \"remove_filler_words\": {\n    \"default\": true,\n    \"description\": \"When true (default), return a cleaned transcript with disfluencies removed. When false, preserve filler words and disfluencies; this path does not support diarization or max_alternatives greater than 1.\",\n    \"required\": false,\n    \"type\": \"boolean\"\n  }\n}\n```\n\nFile v1.0.2:skill-card.md\n\n## Description: <br>\nTranscribes audio from a file ID or public HTTPS URL into text, SRT, WebVTT, or JSON with optional speaker diarization and word timestamps. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[agentpmt](https://clawhub.ai/user/agentpmt) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and developers use this skill to transcribe meetings, interviews, podcasts, webinars, and voice memos through AgentPMT-hosted remote tool calls. It supports selectable transcript formats, length tiers up to 60 minutes, and optional controls for diarization, word timestamps, profanity filtering, and alternative transcripts. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: User-provided audio files or public audio URLs are sent to AgentPMT-hosted transcription infrastructure and may be processed by transcription providers. <br>\nMitigation: Avoid submitting confidential, regulated, or third-party recordings unless the user has permission and accepts the applicable retention and privacy terms. <br>\nRisk: Public URL transcription requires an HTTPS URL and should not target private or internal network resources. <br>\nMitigation: Use only downloadable public HTTPS audio URLs or a file ID from an approved upload flow. <br>\nRisk: Some transcription options are mutually constrained; preserving filler words does not support diarization or more than one alternative transcript. <br>\nMitigation: Check the live schema or generated schema before production integrations and adjust parameters before retrying failed calls. <br>\n\n\n## Reference(s): <br>\n- [Speech To Text With Speakers on ClawHub](https://clawhub.ai/agentpmt/skills/speech-to-text-with-speakers) <br>\n- [AgentPMT Marketplace Product](https://www.agentpmt.com/marketplace/speech-to-text-with-speakers) <br>\n- [Generated Action Schema](artifact/schema.md) <br>\n- [AgentPMT account MCP/REST setup](https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, configuration, guidance] <br>\n**Output Format:** [Markdown guidance with JSON tool-call examples; tool responses may return text, SRT, WebVTT, or JSON transcripts.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Outputs may include speaker labels, word-level timestamps, subtitle content, stored file links, profanity filtering, and alternative transcripts when requested and supported.] <br>\n\n## Skill Version(s): <br>\n1.0.2 (source: evidence.release.version and SKILL.md frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.1: 4 files, 7097 bytes\n\nFiles: schema.md (12133b), skill-card.md (2764b), SKILL.md (12571b), _meta.json (147b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: speech-to-text-with-speakers\ndescription: \"Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an agent needs speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, transcribe extended, file id, public url through AgentPMT-hosted remote tool calls. Discovery terms: speech to text with speakers.\"\nversion: 1.0.1\nhomepage: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\ncompatibility: \"Agent instructions for AgentPMT-hosted remote tool calls. Follow this skill body for supported account, wallet, and setup routes. No local command runtime is declared.\"\nmetadata: {\"author\":\"agentpmt\",\"openclaw\":{\"homepage\":\"https://www.agentpmt.com/marketplace/speech-to-text-with-\n\nArchive v1.0.0: 4 files, 6769 bytes\n\nFiles: schema.md (10984b), skill-card.md (2746b), SKILL.md (11811b), _meta.json (147b)","readmeExcerpt":"Skill: Speech To Text With Speakers Owner: agentpmt Summary: Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an a... Tags: agentpmt:1.0.6, get-task:1.0.6, latest:1.0.6, list-tasks:1.0.6, marketplace:1.0.6, transcribe-extended:1.0.6, transcribe-quick:1.0.6, transcribe-standard:1.0.6 Version history: v1.0.6 | 2026-0","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"{\n  \"action\": \"get_instructions\"\n}"},{"language":"json","snippet":"{\n  \"action\": \"transcribe_quick\",\n  \"file_id\": \"FILE_ID\",\n  \"language_code\": \"en-US\",\n  \"output_format\": \"text\"\n}"},{"language":"json","snippet":"{\n  \"action\": \"transcribe_standard\",\n  \"public_url\": \"https://example.com/meeting.m4a\",\n  \"output_format\": \"vtt\",\n  \"enable_word_timestamps\": true,\n  \"enable_diarization\": true\n}"},{"language":"json","snippet":"{\n  \"action\": \"transcribe_extended\",\n  \"public_url\": \"https://example.com/interview.webm\",\n  \"output_format\": \"json\",\n  \"max_alternatives\": 2\n}"},{"language":"json","snippet":"{\n  \"action\": \"get_task\",\n  \"task_id\": \"TASK_ID\"\n}"},{"language":"json","snippet":"{\n  \"action\": \"list_tasks\",\n  \"limit\": 20\n}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: speech-to-text-with-speakers\ndescription: \"Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an agent needs speech to text with speakers, transcribe meeting recordings, generate subtitles and captions for videos, convert voice memos to searchable text, transcribe podcast episodes, get task, task id, list tasks through AgentPMT-hosted remote tool calls. Discovery terms: speech to text with speakers, transcribe meeting recordings.\"\nversion: 1.0.6\nhomepage: https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\ncompatibility: \"Agent instructions for AgentPMT-hosted remote tool calls. Follow this skill body for supported account, wallet, and setup routes. No local command runtime is declared.\"\nmetadata: {\"author\":\"agentpmt\",\"openclaw\":{\"homepage\":\"https://www.agentpmt.com/marketplace/speech-to-text-with-speakers\"}}\n---\n# Speech to Text With Speakers\n\n## Freshness\nLast updated: `2026-07-22`.\n\nIf the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.\n\n## What This Tool Does\nTurn any audio recording into clean, searchable text in seconds. Transcribe voice memos, meetings, interviews, podcasts, and webinars with accurate speech recognition that handles accents and background noise. Get plain text for quick reference, SRT or WebVTT subtitles for video captioning, or rich JSON output with word-level timestamps and speaker identification. Choose from three tiers based on recording length — up to 15, 30, or 60 minutes — and optionally enable speaker diarization to label who said what, profanity filtering, and alternative transcripts for maximum accuracy.\n\n## Product Instructions\n### Speech to Text\n\nTranscribe audio with one tool. Transcribe actions run as background tasks: the submit response returns a `task_id` immediately, and short clips usually complete inline in that same response. Poll `get_task` for anything still processing.\n\n#### Tool Call Format\n\n```json\n{\n  \"action\": \"get_instructions\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_quick\",\n  \"file_id\": \"FILE_ID\",\n  \"language_code\": \"en-US\",\n  \"output_format\": \"text\"\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_standard\",\n  \"public_url\": \"https://example.com/meeting.m4a\",\n  \"output_format\": \"vtt\",\n  \"enable_word_timestamps\": true,\n  \"enable_diarization\": true\n}\n```\n\n```json\n{\n  \"action\": \"transcribe_extended\",\n  \"public_url\": \"https://example.com/interview.webm\",\n  \"output_format\": \"json\",\n  \"max_alternatives\": 2\n}\n```\n\n```json\n{\n  \"action\": \"get_task\",\n  \"task_id\": \"TASK_ID\"\n}\n```\n\n```json\n{\n  \"action\": \"list_tasks\",\n  \"limit\": 20\n}\n```\n\n#### Actions\n\n- `transcribe_quick`: audio up to 15 minutes. Price: 100 credits.\n- `transcribe_standard`: audio up to 30 minutes. Price: 150 credits.\n- `transcribe_extended`: audio up to 60 minutes. Price: 200 credits.\n- `get_task`: "},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn798pfbxm62kkd2750t7vsex5819pyc\",\n  \"slug\": \"speech-to-text-with-speakers\",\n  \"version\": \"1.0.6\",\n  \"publishedAt\": 1784679952451\n}"},{"path":"schema.md","content":"# Speech to Text With Speakers Schema\n\nThis generated reference belongs to the adjacent `SKILL.md`. Use it for exact action names, action slugs, parameter summaries, sample parameters, and generated JSON parameter schemas.\n\nProduct slug: `speech-to-text-with-speakers`\n\nx402 availability: not enabled for this product.\n\n## `get_task`\n\nAction slug: `get-task`\n\nPrice: `1` credits\n\nCheck a transcription task's progress and retrieve its result. Completed tasks carry the full transcription payload in outputs[0].\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `task_id` | `string` | yes | Task ID returned by a transcribe action. |\n\nSample parameters:\n\n```json\n{\n  \"task_id\": \"example task id\"\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"task_id\": {\n    \"description\": \"Task ID returned by a transcribe action.\",\n    \"required\": true,\n    \"type\": \"string\"\n  }\n}\n```\n\n## `list_tasks`\n\nAction slug: `list-tasks`\n\nPrice: `1` credits\n\nList recent transcription tasks with status and progress.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `limit` | `integer` | no | Maximum number of tasks to return. |\n\nSample parameters:\n\n```json\n{\n  \"limit\": 20\n}\n```\n\nGenerated JSON parameter schema:\n\n```json\n{\n  \"limit\": {\n    \"default\": 20,\n    \"description\": \"Maximum number of tasks to return.\",\n    \"maximum\": 100,\n    \"minimum\": 1,\n    \"required\": false,\n    \"type\": \"integer\"\n  }\n}\n```\n\n## `transcribe_extended`\n\nAction slug: `transcribe-extended`\n\nPrice: `200` credits\n\nStart an asynchronous transcription of audio up to 60 minutes. Returns a task_id immediately (short clips complete inline in the same response); poll get_task for the completed transcript and File Manager artifact.\n\nParameters:\n\n| Parameter | Type | Required | Description |\n|---|---|---|---|\n| `enable_diarization` | `boolean` | no | Enable speaker diarization when supported by the audio and model. Not supported when remove_filler_words is false. |\n| `enable_profanity_filter` | `boolean` | no | Mask profanity in the returned transcript. |\n| `enable_word_timestamps` | `boolean` | no | Include word-level timing data in the output. |\n| `file_id` | `string` | no | File ID from a prior upload. Provide either file_id or public_url. |\n| `language_code` | `string` | no | Optional BCP-47 language code such as en-US; defaults to en-US if omitted. |\n| `max_alternatives` | `integer` | no | Maximum number of alternative transcripts to return. Must be 1 when remove_filler_words is false. |\n| `output_format` | `string` | no | Output format for the transcription result. The completed task's outputs include the selected content inline plus result_file_id and result_signed_url for the File Manager artifact. |\n| `public_url` | `string` | no | HTTPS URL to a downloadable audio file. Provide either public_url or file_id. |\n| `remove_filler_words` | `boolean` | no | When true (default), return a cleaned transcript with disfluencies removed. When false, preserve "},{"path":"skill-card.md","content":"## Description:\n\nTranscribes audio from an uploaded file_id or public HTTPS URL into text, SRT, WebVTT, or JSON with optional word timestamps, profanity filtering, alternatives, and speaker diarization through AgentPMT-hosted remote calls.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[agentpmt](https://clawhub.ai/user/agentpmt)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to submit meeting recordings, voice memos, interviews, podcasts, webinars, and similar audio for transcription, then poll task status and retrieve transcript outputs with optional speaker labels and timing data.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Audio supplied by file_id or public URL is processed by AgentPMT and transcription providers.\n\nMitigation: Avoid confidential or regulated recordings unless the user's organization permits that processing.\n\nRisk: npx-based setup steps may introduce supply-chain exposure.\n\nMitigation: Prefer the OpenClaw install route, or verify and pin setup dependencies before running npx commands.\n\nRisk: Selecting a tier below the recording length can fail after submission and may still consume credits.\n\nMitigation: Choose the tier from the known recording length and review error_details.recommended_actions before resubmitting.\n\n## Reference(s):\n\n- [Speech To Text With Speakers ClawHub Page](https://clawhub.ai/agentpmt/skills/speech-to-text-with-speakers)\n- [AgentPMT Marketplace Product](https://www.agentpmt.com/marketplace/speech-to-text-with-speakers)\n- [Speech To Text With Speakers Schema](artifact/schema.md)\n- [AgentPMT Account MCP/REST Setup](https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup)\n- [AgentPMT File Management](https://clawhub.ai/agentpmt/file-management)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, JSON, Configuration guidance]\n\n**Output Format:** [Markdown guidance with JSON tool-call examples; task outputs may include plain text, SRT, WebVTT, or structured JSON.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Transcription jobs run asynchronously; completed tasks can include inline transcript content, speaker data, timing metadata, and File Manager artifact identifiers.]\n\n## Skill Version(s):\n\n1.0.6 (source: frontmatter and server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1480,"uniquenessScore":41,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T02:22:50.548Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-12T02:22:50.548Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-13T01:47:17.496Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}