{"id":"ae318661-51bc-4abc-94ad-df84294744ea","entityType":"agent","slug":"clawhub-wavespeed-wavespeed-minimax-speech-26","name":"WaveSpeedAI MiniMax Speech 2.6 TTS","canonicalUrl":"https://www.xpersona.co/agent/clawhub-wavespeed-wavespeed-minimax-speech-26","canonicalPath":"/agent/clawhub-wavespeed-wavespeed-minimax-speech-26","generatedAt":"2026-10-11T20:57:05.230Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T15:48:26.887Z","emptyReason":null},"description":"Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text. Skill: WaveSpeedAI MiniMax Speech 2.6 TTS Owner: wavespeed Summary: Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text. Tags: latest:2.0.1 Version history: v2.0.1 | 2026-09-05T16:30:03.766Z | user Moved to the @wavespeed organiza","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17epnq4kcsv1261rq3e9gvwcx8dth5q:wavespeed-minimax-speech-26","sourceUrl":"https://clawhub.ai/wavespeed/wavespeed-minimax-speech-26","homepage":"https://clawhub.ai/wavespeed/skills/wavespeed-minimax-speech-26","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/wavespeed/wavespeed-minimax-speech-26","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/wavespeed/skills/wavespeed-minimax-speech-26","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, a"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:48:26.887Z","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":"2026-10-11T15:48:26.887Z","emptyReason":null},"stars":null,"forks":null,"downloads":1035,"packageName":null,"latestVersion":"2.0.1","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:48:26.818Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T15:48:26.887Z","lastCrawledAt":"2026-10-11T15:48:26.818Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T15:48:26.818Z","lastVerifiedAt":null,"highlights":[{"version":"2.0.1","createdAt":"2026-09-05T16:30:03.766Z","changelog":"Moved to the @wavespeed organization.","fileCount":3,"zipByteSize":4753},{"version":"2.0.0","createdAt":"2026-09-05T16:17:08.778Z","changelog":"Examples switched from the JS SDK to the wavespeed CLI (with the @wavespeed/mcp server as the MCP alternative): install + login setup, @path local-file upload, price quotes, --json output. SDK-specific sections (sync mode, custom client, runNoThrow) removed.","fileCount":3,"zipByteSize":5002},{"version":"1.0.0","createdAt":"2026-03-03T07:28:12.456Z","changelog":"Initial release of wavespeed-minimax-speech-26, enabling high-quality text-to-speech via the MiniMax Speech 2.6 Turbo model: - Supports ultra-human voice cloning, emotion control, and sub-250ms latency. - Over 200 voice presets in 40+ languages, including advanced voice and pause control. - Detailed SDK and API usage instructions: configuration, error handling, and advanced options. - Flexible output settings: speed, pitch, volume, format, sample rate, and bitrate. - Secure API key management and clear input validation guidance.","fileCount":3,"zipByteSize":4465}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17epnq4kcsv1261rq3e9gvwcx8dth5q:wavespeed-minimax-speech-26","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"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-wavespeed-wavespeed-minimax-speech-26/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-minimax-speech-26/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-minimax-speech-26/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-minimax-speech-26/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-minimax-speech-26/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-minimax-speech-26/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T20:57:05.229Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-minimax-speech-26/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-minimax-speech-26/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-minimax-speech-26/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-minimax-speech-26/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":"high","updatedAt":"2026-10-11T15:48:26.887Z","emptyReason":null},"readme":"Skill: WaveSpeedAI MiniMax Speech 2.6 TTS\n\nOwner: wavespeed\n\nSummary: Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text.\n\nTags: latest:2.0.1\n\nVersion history:\n\nv2.0.1 | 2026-09-05T16:30:03.766Z | user\n\nMoved to the @wavespeed organization.\n\nv2.0.0 | 2026-09-05T16:17:08.778Z | user\n\nExamples switched from the JS SDK to the wavespeed CLI (with the @wavespeed/mcp server as the MCP alternative): install + login setup, @path local-file upload, price quotes, --json output. SDK-specific sections (sync mode, custom client, runNoThrow) removed.\n\nv1.0.0 | 2026-03-03T07:28:12.456Z | user\n\nInitial release of wavespeed-minimax-speech-26, enabling high-quality text-to-speech via the MiniMax Speech 2.6 Turbo model:\n\n- Supports ultra-human voice cloning, emotion control, and sub-250ms latency.\n- Over 200 voice presets in 40+ languages, including advanced voice and pause control.\n- Detailed SDK and API usage instructions: configuration, error handling, and advanced options.\n- Flexible output settings: speed, pitch, volume, format, sample rate, and bitrate.\n- Secure API key management and clear input validation guidance.\n\nArchive index:\n\nArchive v2.0.1: 3 files, 4753 bytes\n\nFiles: skill-card.md (2035b), SKILL.md (7385b), _meta.json (146b)\n\nFile v2.0.1:SKILL.md\n\n---\nname: wavespeed-minimax-speech-26\ndescription: Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text.\nmetadata:\n author: wavespeedai\n version: \"2.0\"\n---\n\n# WaveSpeedAI MiniMax Speech 2.6 Turbo\n\nConvert text to speech using MiniMax Speech 2.6 Turbo via the WaveSpeed AI platform. Features ultra-human voice cloning, sub-250ms latency, 40+ language support, and emotion control.\n\n## Setup\n\nInstall the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:\n\n```bash\nnpm install -g @wavespeed/cli\nwavespeed login # opens https://wavespeed.ai/accesskey and stores the key\nwavespeed status # confirms you are signed in\n```\n\nFor CI or one-off shells, `WAVESPEED_API_KEY` in the environment also works.\n\nPrefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). It shares the CLI's stored login. Every example below maps one-to-one onto `run_model` with the same model id and input fields.\n\n## Quick Start\n\n```bash\nOUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"Hello, welcome to WaveSpeed AI!\" \\\n -i voice_id=\"English_CalmWoman\" \\\n --json | jq -r '.outputs[0]')\n```\n\n## API Endpoint\n\n**Model ID:** `minimax/speech-2.6-turbo`\n\nConvert text to speech with configurable voice, emotion, speed, pitch, and audio format.\n\n### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `text` | string | Yes | -- | Text to convert to speech. Max 10,000 characters. Use `<#x#>` between words to insert pauses (0.01-99.99 seconds). |\n| `voice_id` | string | Yes | -- | Voice preset ID. See [Voice IDs](#voice-ids) below. |\n| `speed` | number | No | `1` | Speech speed. Range: 0.50-2.00 |\n| `volume` | number | No | `1` | Speech volume. Range: 0.10-10.00 |\n| `pitch` | number | No | `0` | Speech pitch. Range: -12 to 12 |\n| `emotion` | string | No | `happy` | Emotional tone. One of: `happy`, `sad`, `angry`, `fearful`, `disgusted`, `surprised`, `neutral` |\n| `english_normalization` | boolean | No | `false` | Improve English number reading normalization |\n| `sample_rate` | integer | No | -- | Sample rate in Hz. One of: `8000`, `16000`, `22050`, `24000`, `32000`, `44100` |\n| `bitrate` | integer | No | -- | Bitrate in bps. One of: `32000`, `64000`, `128000`, `256000` |\n| `channel` | string | No | -- | Audio channels. `1` (mono) or `2` (stereo) |\n| `format` | string | No | -- | Output format. One of: `mp3`, `wav`, `pcm`, `flac` |\n| `language_boost` | string | No | -- | Enhance recognition for a specific language. See [Supported Languages](#supported-languages). |\n\n### Example\n\n```bash\nOUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"The quick brown fox jumps over the lazy dog.\" \\\n -i voice_id=\"English_expressive_narrator\" \\\n -i speed=1.0 \\\n -i pitch=0 \\\n -i emotion=\"neutral\" \\\n -i format=\"mp3\" \\\n -i sample_rate=24000 \\\n -i bitrate=128000 \\\n --json | jq -r '.outputs[0]')\n```\n\n### Pause Control\n\nInsert pauses in speech using `<#x#>` syntax where `x` is seconds (0.01-99.99):\n\n```bash\nOUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"And the winner is <#2.0#> WaveSpeed AI!\" \\\n -i voice_id=\"English_CaptivatingStoryteller\" \\\n --json | jq -r '.outputs[0]')\n```\n\n\n## Voice IDs\n\n### English Voices (Popular)\n\n| Voice ID | Description |\n|----------|-------------|\n| `English_CalmWoman` | Calm female voice |\n| `English_Trustworth_Man` | Trustworthy male voice |\n| `English_expressive_narrator` | Expressive narrator |\n| `English_radiant_girl` | Radiant girl voice |\n| `English_magnetic_voiced_man` | Magnetic male voice |\n| `English_CaptivatingStoryteller` | Storyteller voice |\n| `English_Upbeat_Woman` | Upbeat female voice |\n| `English_GentleTeacher` | Gentle teacher voice |\n| `English_PlayfulGirl` | Playful girl voice |\n| `English_ManWithDeepVoice` | Deep male voice |\n| `English_ConfidentWoman` | Confident female voice |\n| `English_Comedian` | Comedic voice |\n| `English_SereneWoman` | Serene female voice |\n| `English_WiseScholar` | Scholarly voice |\n| `English_Cute_Girl` | Cute girl voice |\n| `English_Sharp_Commentator` | Sharp commentator |\n| `English_Lucky_Robot` | Robot voice |\n\n### General Voices\n\n`Wise_Woman`, `Friendly_Person`, `Inspirational_girl`, `Deep_Voice_Man`, `Calm_Woman`, `Casual_Guy`, `Lively_Girl`, `Patient_Man`, `Young_Knight`, `Determined_Man`, `Lovely_Girl`, `Decent_Boy`, `Imposing_Manner`, `Elegant_Man`, `Abbess`, `Sweet_Girl_2`, `Exuberant_Girl`\n\n### Special Voices\n\n`whisper_man`, `whisper_woman_1`, `angry_pirate_1`, `massive_kind_troll`, `movie_trailer_deep`, `peace_and_ease`\n\n### Other Languages\n\nVoices are available for: Chinese (Mandarin), Cantonese, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans.\n\nVoice IDs follow the pattern `{Language}_{VoiceName}` (e.g., `Japanese_KindLady`, `Korean_SweetGirl`, `French_CasualMan`).\n\n## Supported Languages\n\nFor `language_boost`: `Chinese`, `Chinese,Yue`, `English`, `Arabic`, `Russian`, `Spanish`, `French`, `Portuguese`, `German`, `Turkish`, `Dutch`, `Ukrainian`, `Vietnamese`, `Indonesian`, `Japanese`, `Italian`, `Korean`, `Thai`, `Polish`, `Romanian`, `Greek`, `Czech`, `Finnish`, `Hindi`, `Bulgarian`, `Danish`, `Hebrew`, `Malay`, `Persian`, `Slovak`, `Swedish`, `Croatian`, `Filipino`, `Hungarian`, `Norwegian`, `Slovenian`, `Catalan`, `Nynorsk`, `Tamil`, `Afrikaans`\n\n## Pricing\n\n$0.06 per 1,000 characters.\n\n## CLI tips\n\n```bash\n# Inspect the live input schema before running (fields, enums, defaults)\nwavespeed run minimax/speech-2.6-turbo -h\n\n# Quote the price first\nwavespeed price minimax/speech-2.6-turbo -p \"...\" -i key=value\n\n# Save outputs to disk instead of only printing URLs\nwavespeed run minimax/speech-2.6-turbo -p \"...\" --json --download \"./out/{index}.{ext}\"\n\n# Local files: prefix the path with @ and the CLI uploads it and passes the hosted URL\nwavespeed run minimax/speech-2.6-turbo -i =@./local-file.png --json\n\n# Recover a result if the run was interrupted (the id is in the --json output)\nwavespeed show \n```\n\n`run --json` prints `{ id, model, prompt, outputs: [url, ...], saved: [path, ...], elapsed_ms, raw }`. Read `outputs[0]` for the result URL.\n\n## Security constraints\n\n- **Never ask for the key in chat**: `wavespeed login` handles auth; if `wavespeed status` says signed out, ask the user to run it.\n- **Local files only via `@`**: bare paths are passed through untouched and the model will reject them. Only `@`-prefixed values upload.\n- **No arbitrary URL loading**: only pass media URLs the user provided or that came back from a previous run.\n- **Input validation**: only pass parameters documented above; confirm with `wavespeed run -h` when unsure.\n\nFile v2.0.1:_meta.json\n\n{\n \"ownerId\": \"kn733k72mbe41a710dd1kfpg2s8257bs\",\n \"slug\": \"wavespeed-minimax-speech-26\",\n \"version\": \"2.0.1\",\n \"publishedAt\": 1788625803766\n}\n\nFile v2.0.1:skill-card.md\n\n## Description:\n\nConvert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI, with voice cloning, low-latency speech generation, multilingual support, emotion control, and voice presets.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[wavespeed](https://clawhub.ai/user/wavespeed)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent users use this skill to generate speech audio from text through WaveSpeed AI's MiniMax Speech 2.6 Turbo model. It helps configure voice, emotion, speed, pitch, language, and audio output settings.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Unpinned npm CLI or npx MCP setup can introduce normal package supply-chain risk.\n\nMitigation: Use pinned, reviewed package versions in sensitive environments.\n\nRisk: Text submitted for speech generation is sent to WaveSpeed AI.\n\nMitigation: Install and use the skill only when that service is acceptable for the text or files being processed.\n\nRisk: API keys may be exposed if pasted into chat.\n\nMitigation: Use the documented login flow or environment variable handling instead of sharing keys in chat.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/wavespeed/skills/wavespeed-minimax-speech-26)\n- [WaveSpeed MCP server](https://github.com/WaveSpeedAI/mcp-server)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands, Configuration instructions, API Calls]\n\n**Output Format:** [Markdown with inline bash commands and parameter guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [The skill guides text-to-speech requests that return generated audio URLs or downloaded audio files.]\n\n## Skill Version(s):\n\n2.0.1 (source: server release evidence)\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 v2.0.0: 3 files, 5002 bytes\n\nFiles: skill-card.md (2560b), SKILL.md (7385b), _meta.json (146b)\n\nFile v2.0.0:SKILL.md\n\n---\nname: wavespeed-minimax-speech-26\ndescription: Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text.\nmetadata:\n author: wavespeedai\n version: \"2.0\"\n---\n\n# WaveSpeedAI MiniMax Speech 2.6 Turbo\n\nConvert text to speech using MiniMax Speech 2.6 Turbo via the WaveSpeed AI platform. Features ultra-human voice cloning, sub-250ms latency, 40+ language support, and emotion control.\n\n## Setup\n\nInstall the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:\n\n```bash\nnpm install -g @wavespeed/cli\nwavespeed login # opens https://wavespeed.ai/accesskey and stores the key\nwavespeed status # confirms you are signed in\n```\n\nFor CI or one-off shells, `WAVESPEED_API_KEY` in the environment also works.\n\nPrefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). It shares the CLI's stored login. Every example below maps one-to-one onto `run_model` with the same model id and input fields.\n\n## Quick Start\n\n```bash\nOUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"Hello, welcome to WaveSpeed AI!\" \\\n -i voice_id=\"English_CalmWoman\" \\\n --json | jq -r '.outputs[0]')\n```\n\n## API Endpoint\n\n**Model ID:** `minimax/speech-2.6-turbo`\n\nConvert text to speech with configurable voice, emotion, speed, pitch, and audio format.\n\n### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `text` | string | Yes | -- | Text to convert to speech. Max 10,000 characters. Use `<#x#>` between words to insert pauses (0.01-99.99 seconds). |\n| `voice_id` | string | Yes | -- | Voice preset ID. See [Voice IDs](#voice-ids) below. |\n| `speed` | number | No | `1` | Speech speed. Range: 0.50-2.00 |\n| `volume` | number | No | `1` | Speech volume. Range: 0.10-10.00 |\n| `pitch` | number | No | `0` | Speech pitch. Range: -12 to 12 |\n| `emotion` | string | No | `happy` | Emotional tone. One of: `happy`, `sad`, `angry`, `fearful`, `disgusted`, `surprised`, `neutral` |\n| `english_normalization` | boolean | No | `false` | Improve English number reading normalization |\n| `sample_rate` | integer | No | -- | Sample rate in Hz. One of: `8000`, `16000`, `22050`, `24000`, `32000`, `44100` |\n| `bitrate` | integer | No | -- | Bitrate in bps. One of: `32000`, `64000`, `128000`, `256000` |\n| `channel` | string | No | -- | Audio channels. `1` (mono) or `2` (stereo) |\n| `format` | string | No | -- | Output format. One of: `mp3`, `wav`, `pcm`, `flac` |\n| `language_boost` | string | No | -- | Enhance recognition for a specific language. See [Supported Languages](#supported-languages). |\n\n### Example\n\n```bash\nOUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"The quick brown fox jumps over the lazy dog.\" \\\n -i voice_id=\"English_expressive_narrator\" \\\n -i speed=1.0 \\\n -i pitch=0 \\\n -i emotion=\"neutral\" \\\n -i format=\"mp3\" \\\n -i sample_rate=24000 \\\n -i bitrate=128000 \\\n --json | jq -r '.outputs[0]')\n```\n\n### Pause Control\n\nInsert pauses in speech using `<#x#>` syntax where `x` is seconds (0.01-99.99):\n\n```bash\nOUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"And the winner is <#2.0#> WaveSpeed AI!\" \\\n -i voice_id=\"English_CaptivatingStoryteller\" \\\n --json | jq -r '.outputs[0]')\n```\n\n\n## Voice IDs\n\n### English Voices (Popular)\n\n| Voice ID | Description |\n|----------|-------------|\n| `English_CalmWoman` | Calm female voice |\n| `English_Trustworth_Man` | Trustworthy male voice |\n| `English_expressive_narrator` | Expressive narrator |\n| `English_radiant_girl` | Radiant girl voice |\n| `English_magnetic_voiced_man` | Magnetic male voice |\n| `English_CaptivatingStoryteller` | Storyteller voice |\n| `English_Upbeat_Woman` | Upbeat female voice |\n| `English_GentleTeacher` | Gentle teacher voice |\n| `English_PlayfulGirl` | Playful girl voice |\n| `English_ManWithDeepVoice` | Deep male voice |\n| `English_ConfidentWoman` | Confident female voice |\n| `English_Comedian` | Comedic voice |\n| `English_SereneWoman` | Serene female voice |\n| `English_WiseScholar` | Scholarly voice |\n| `English_Cute_Girl` | Cute girl voice |\n| `English_Sharp_Commentator` | Sharp commentator |\n| `English_Lucky_Robot` | Robot voice |\n\n### General Voices\n\n`Wise_Woman`, `Friendly_Person`, `Inspirational_girl`, `Deep_Voice_Man`, `Calm_Woman`, `Casual_Guy`, `Lively_Girl`, `Patient_Man`, `Young_Knight`, `Determined_Man`, `Lovely_Girl`, `Decent_Boy`, `Imposing_Manner`, `Elegant_Man`, `Abbess`, `Sweet_Girl_2`, `Exuberant_Girl`\n\n### Special Voices\n\n`whisper_man`, `whisper_woman_1`, `angry_pirate_1`, `massive_kind_troll`, `movie_trailer_deep`, `peace_and_ease`\n\n### Other Languages\n\nVoices are available for: Chinese (Mandarin), Cantonese, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans.\n\nVoice IDs follow the pattern `{Language}_{VoiceName}` (e.g., `Japanese_KindLady`, `Korean_SweetGirl`, `French_CasualMan`).\n\n## Supported Languages\n\nFor `language_boost`: `Chinese`, `Chinese,Yue`, `English`, `Arabic`, `Russian`, `Spanish`, `French`, `Portuguese`, `German`, `Turkish`, `Dutch`, `Ukrainian`, `Vietnamese`, `Indonesian`, `Japanese`, `Italian`, `Korean`, `Thai`, `Polish`, `Romanian`, `Greek`, `Czech`, `Finnish`, `Hindi`, `Bulgarian`, `Danish`, `Hebrew`, `Malay`, `Persian`, `Slovak`, `Swedish`, `Croatian`, `Filipino`, `Hungarian`, `Norwegian`, `Slovenian`, `Catalan`, `Nynorsk`, `Tamil`, `Afrikaans`\n\n## Pricing\n\n$0.06 per 1,000 characters.\n\n## CLI tips\n\n```bash\n# Inspect the live input schema before running (fields, enums, defaults)\nwavespeed run minimax/speech-2.6-turbo -h\n\n# Quote the price first\nwavespeed price minimax/speech-2.6-turbo -p \"...\" -i key=value\n\n# Save outputs to disk instead of only printing URLs\nwavespeed run minimax/speech-2.6-turbo -p \"...\" --json --download \"./out/{index}.{ext}\"\n\n# Local files: prefix the path with @ and the CLI uploads it and passes the hosted URL\nwavespeed run minimax/speech-2.6-turbo -i =@./local-file.png --json\n\n# Recover a result if the run was interrupted (the id is in the --json output)\nwavespeed show \n```\n\n`run --json` prints `{ id, model, prompt, outputs: [url, ...], saved: [path, ...], elapsed_ms, raw }`. Read `outputs[0]` for the result URL.\n\n## Security constraints\n\n- **Never ask for the key in chat**: `wavespeed login` handles auth; if `wavespeed status` says signed out, ask the user to run it.\n- **Local files only via `@`**: bare paths are passed through untouched and the model will reject them. Only `@`-prefixed values upload.\n- **No arbitrary URL loading**: only pass media URLs the user provided or that came back from a previous run.\n- **Input validation**: only pass parameters documented above; confirm with `wavespeed run -h` when unsure.\n\nFile v2.0.0:_meta.json\n\n{\n \"ownerId\": \"kn733k72mbe41a710dd1kfpg2s8257bs\",\n \"slug\": \"wavespeed-minimax-speech-26\",\n \"version\": \"2.0.0\",\n \"publishedAt\": 1788625028778\n}\n\nFile v2.0.0:skill-card.md\n\n## Description:\n\nConvert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI, with voice cloning, low-latency generation, multilingual voices, emotion control, and voice presets.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[chengzeyi](https://clawhub.ai/user/chengzeyi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to generate speech audio from text with MiniMax Speech 2.6 Turbo through WaveSpeed AI. It helps configure voices, speech style, audio format, pricing checks, and CLI or MCP execution paths.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill directs agents to install and run WaveSpeed npm packages and CLI commands locally.\n\nMitigation: Use a trusted, pinned, project-local install or prefer structured MCP/API calls where available.\n\nRisk: The WaveSpeed CLI stores a credential and also supports WAVESPEED_API_KEY for automation.\n\nMitigation: Do not request secrets in chat; use wavespeed login or environment-secret handling and verify account state with wavespeed status.\n\nRisk: Generated shell commands may include user-provided speech text or file references.\n\nMitigation: Avoid constructing shell commands from untrusted text without quoting and validation; pass only documented parameters and @-prefixed local files.\n\nRisk: Text, regulated data, voice samples, or other sensitive content could be submitted to an external TTS service.\n\nMitigation: Confirm user permission and data suitability before submitting content, and avoid secrets or regulated data.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/chengzeyi/skills/wavespeed-minimax-speech-26)\n- [WaveSpeed MCP server](https://github.com/WaveSpeedAI/mcp-server)\n- [WaveSpeed access key page](https://wavespeed.ai/accesskey)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with inline bash code blocks and parameter tables]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May produce WaveSpeed CLI commands that return JSON containing output audio URLs or downloaded audio paths.]\n\n## Skill Version(s):\n\n2.0.0 (source: server release metadata; artifact frontmatter reports 2.0)\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 v1.0.0: 3 files, 4465 bytes\n\nFiles: skill-card.md (2240b), SKILL.md (7275b), _meta.json (146b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: wavespeed-minimax-speech-26\ndescription: Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text.\nmetadata:\n author: wavespeedai\n version: \"1.0\"\n---\n\n# WaveSpeedAI MiniMax Speech 2.6 Turbo\n\nConvert text to speech using MiniMax Speech 2.6 Turbo via the WaveSpeed AI platform. Features ultra-human voice cloning, sub-250ms latency, 40+ language support, and emotion control.\n\n## Authentication\n\n```bash\nexport WAVESPEED_API_KEY=\"your-api-key\"\n```\n\nGet your API key at [wavespeed.ai/accesskey](https://wavespeed.ai/accesskey).\n\n## Quick Start\n\n```javascript\nimport wavespeed from 'wavespeed';\n\nconst output_url = (await wavespeed.run(\n \"minimax/speech-2.6-turbo\",\n {\n text: \"Hello, welcome to WaveSpeed AI!\",\n voice_id: \"English_CalmWoman\"\n }\n))[\"outputs\"][0];\n```\n\n## API Endpoint\n\n**Model ID:** `minimax/speech-2.6-turbo`\n\nConvert text to speech with configurable voice, emotion, speed, pitch, and audio format.\n\n### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `text` | string | Yes | -- | Text to convert to speech. Max 10,000 characters. Use `<#x#>` between words to insert pauses (0.01-99.99 seconds). |\n| `voice_id` | string | Yes | -- | Voice preset ID. See [Voice IDs](#voice-ids) below. |\n| `speed` | number | No | `1` | Speech speed. Range: 0.50-2.00 |\n| `volume` | number | No | `1` | Speech volume. Range: 0.10-10.00 |\n| `pitch` | number | No | `0` | Speech pitch. Range: -12 to 12 |\n| `emotion` | string | No | `happy` | Emotional tone. One of: `happy`, `sad`, `angry`, `fearful`, `disgusted`, `surprised`, `neutral` |\n| `english_normalization` | boolean | No | `false` | Improve English number reading normalization |\n| `sample_rate` | integer | No | -- | Sample rate in Hz. One of: `8000`, `16000`, `22050`, `24000`, `32000`, `44100` |\n| `bitrate` | integer | No | -- | Bitrate in bps. One of: `32000`, `64000`, `128000`, `256000` |\n| `channel` | string | No | -- | Audio channels. `1` (mono) or `2` (stereo) |\n| `format` | string | No | -- | Output format. One of: `mp3`, `wav`, `pcm`, `flac` |\n| `language_boost` | string | No | -- | Enhance recognition for a specific language. See [Supported Languages](#supported-languages). |\n\n### Example\n\n```javascript\nimport wavespeed from 'wavespeed';\n\nconst output_url = (await wavespeed.run(\n \"minimax/speech-2.6-turbo\",\n {\n text: \"The quick brown fox jumps over the lazy dog.\",\n voice_id: \"English_expressive_narrator\",\n speed: 1.0,\n pitch: 0,\n emotion: \"neutral\",\n format: \"mp3\",\n sample_rate: 24000,\n bitrate: 128000\n }\n))[\"outputs\"][0];\n```\n\n### Pause Control\n\nInsert pauses in speech using `<#x#>` syntax where `x` is seconds (0.01-99.99):\n\n```javascript\nconst output_url = (await wavespeed.run(\n \"minimax/speech-2.6-turbo\",\n {\n text: \"And the winner is <#2.0#> WaveSpeed AI!\",\n voice_id: \"English_CaptivatingStoryteller\"\n }\n))[\"outputs\"][0];\n```\n\n## Advanced Usage\n\n### Sync Mode\n\n```javascript\nconst output_url = (await wavespeed.run(\n \"minimax/speech-2.6-turbo\",\n {\n text: \"Hello world!\",\n voice_id: \"English_CalmWoman\"\n },\n { enableSyncMode: true }\n))[\"outputs\"][0];\n```\n\n### Custom Client with Retry Configuration\n\n```javascript\nimport { Client } from 'wavespeed';\n\nconst client = new Client(\"your-api-key\", {\n maxRetries: 2,\n maxConnectionRetries: 5,\n retryInterval: 1.0,\n});\n\nconst output_url = (await client.run(\n \"minimax/speech-2.6-turbo\",\n {\n text: \"Welcome to our platform.\",\n voice_id: \"English_Trustworth_Man\"\n }\n))[\"outputs\"][0];\n```\n\n### Error Handling with runNoThrow\n\n```javascript\nimport { Client, WavespeedTimeoutException, WavespeedPredictionException } from 'wavespeed';\n\nconst client = new Client();\nconst result = await client.runNoThrow(\n \"minimax/speech-2.6-turbo\",\n {\n text: \"Testing speech generation.\",\n voice_id: \"English_CalmWoman\"\n }\n);\n\nif (result.outputs) {\n console.log(\"Audio URL:\", result.outputs[0]);\n console.log(\"Task ID:\", result.detail.taskId);\n} else {\n console.log(\"Failed:\", result.detail.error.message);\n if (result.detail.error instanceof WavespeedTimeoutException) {\n console.log(\"Request timed out - try increasing timeout\");\n } else if (result.detail.error instanceof WavespeedPredictionException) {\n console.log(\"Prediction failed\");\n }\n}\n```\n\n## Voice IDs\n\n### English Voices (Popular)\n\n| Voice ID | Description |\n|----------|-------------|\n| `English_CalmWoman` | Calm female voice |\n| `English_Trustworth_Man` | Trustworthy male voice |\n| `English_expressive_narrator` | Expressive narrator |\n| `English_radiant_girl` | Radiant girl voice |\n| `English_magnetic_voiced_man` | Magnetic male voice |\n| `English_CaptivatingStoryteller` | Storyteller voice |\n| `English_Upbeat_Woman` | Upbeat female voice |\n| `English_GentleTeacher` | Gentle teacher voice |\n| `English_PlayfulGirl` | Playful girl voice |\n| `English_ManWithDeepVoice` | Deep male voice |\n| `English_ConfidentWoman` | Confident female voice |\n| `English_Comedian` | Comedic voice |\n| `English_SereneWoman` | Serene female voice |\n| `English_WiseScholar` | Scholarly voice |\n| `English_Cute_Girl` | Cute girl voice |\n| `English_Sharp_Commentator` | Sharp commentator |\n| `English_Lucky_Robot` | Robot voice |\n\n### General Voices\n\n`Wise_Woman`, `Friendly_Person`, `Inspirational_girl`, `Deep_Voice_Man`, `Calm_Woman`, `Casual_Guy`, `Lively_Girl`, `Patient_Man`, `Young_Knight`, `Determined_Man`, `Lovely_Girl`, `Decent_Boy`, `Imposing_Manner`, `Elegant_Man`, `Abbess`, `Sweet_Girl_2`, `Exuberant_Girl`\n\n### Special Voices\n\n`whisper_man`, `whisper_woman_1`, `angry_pirate_1`, `massive_kind_troll`, `movie_trailer_deep`, `peace_and_ease`\n\n### Other Languages\n\nVoices are available for: Chinese (Mandarin), Cantonese, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans.\n\nVoice IDs follow the pattern `{Language}_{VoiceName}` (e.g., `Japanese_KindLady`, `Korean_SweetGirl`, `French_CasualMan`).\n\n## Supported Languages\n\nFor `language_boost`: `Chinese`, `Chinese,Yue`, `English`, `Arabic`, `Russian`, `Spanish`, `French`, `Portuguese`, `German`, `Turkish`, `Dutch`, `Ukrainian`, `Vietnamese`, `Indonesian`, `Japanese`, `Italian`, `Korean`, `Thai`, `Polish`, `Romanian`, `Greek`, `Czech`, `Finnish`, `Hindi`, `Bulgarian`, `Danish`, `Hebrew`, `Malay`, `Persian`, `Slovak`, `Swedish`, `Croatian`, `Filipino`, `Hungarian`, `Norwegian`, `Slovenian`, `Catalan`, `Nynorsk`, `Tamil`, `Afrikaans`\n\n## Pricing\n\n$0.06 per 1,000 characters.\n\n## Security Constraints\n\n- **API key security**: Store your `WAVESPEED_API_KEY` securely. Do not hardcode it in source files or commit it to version control. Use environment variables or secret management systems.\n- **Input validation**: Only pass parameters documented above. Validate text content before sending requests.\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn733k72mbe41a710dd1kfpg2s8257bs\",\n \"slug\": \"wavespeed-minimax-speech-26\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1772522892456\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:
\nConvert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI with voice presets, emotion controls, language support, and configurable audio output.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[chengzeyi](https://clawhub.ai/user/chengzeyi)
\n\n### License/Terms of Use:
\n\n\n## Use Case:
\nDevelopers and agents use this skill to configure WaveSpeed AI MiniMax Speech 2.6 Turbo text-to-speech requests, choose voices and audio settings, and handle generated audio URLs.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Submitted text is processed by WaveSpeed AI as an external service.
\nMitigation: Do not submit secrets, credentials, regulated data, confidential scripts, or other sensitive text unless the applicable data-sharing policy permits it.
\nRisk: The skill uses a WaveSpeed API key for billable requests.
\nMitigation: Store WAVESPEED_API_KEY in an environment variable or secret manager, avoid hardcoding it, and monitor usage according to account policy.
\nRisk: JavaScript examples depend on the wavespeed client package.
\nMitigation: Verify the official wavespeed client package before running examples and validate request parameters against the documented options.
\n\n\n## Reference(s):
\n- [WaveSpeed AI API Keys](https://wavespeed.ai/accesskey)
\n- [ClawHub Skill Page](https://clawhub.ai/chengzeyi/wavespeed-minimax-speech-26)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, code, shell commands, configuration]
\n**Output Format:** [Markdown with inline bash and JavaScript code blocks]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Guidance covers text, voice, emotion, speed, pitch, audio format, sample rate, bitrate, channel, and language boost settings.]
\n\n## Skill Version(s):
\n1.0.0 (source: server release metadata)
\n\n## Ethical Considerations:
\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.
","readmeExcerpt":"Skill: WaveSpeedAI MiniMax Speech 2.6 TTS Owner: wavespeed Summary: Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text. Tags: latest:2.0.1 Version history: v2.0.1 | 2026-09-05T16:30:03.766Z | user Moved to the @wavespeed organiza","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"npm install -g @wavespeed/cli\nwavespeed login # opens https://wavespeed.ai/accesskey and stores the key\nwavespeed status # confirms you are signed in"},{"language":"bash","snippet":"OUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"Hello, welcome to WaveSpeed AI!\" \\\n -i voice_id=\"English_CalmWoman\" \\\n --json | jq -r '.outputs[0]')"},{"language":"bash","snippet":"OUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"The quick brown fox jumps over the lazy dog.\" \\\n -i voice_id=\"English_expressive_narrator\" \\\n -i speed=1.0 \\\n -i pitch=0 \\\n -i emotion=\"neutral\" \\\n -i format=\"mp3\" \\\n -i sample_rate=24000 \\\n -i bitrate=128000 \\\n --json | jq -r '.outputs[0]')"},{"language":"bash","snippet":"OUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"And the winner is <#2.0#> WaveSpeed AI!\" \\\n -i voice_id=\"English_CaptivatingStoryteller\" \\\n --json | jq -r '.outputs[0]')"},{"language":"bash","snippet":"# Inspect the live input schema before running (fields, enums, defaults)\nwavespeed run minimax/speech-2.6-turbo -h\n\n# Quote the price first\nwavespeed price minimax/speech-2.6-turbo -p \"...\" -i key=value\n\n# Save outputs to disk instead of only printing URLs\nwavespeed run minimax/speech-2.6-turbo -p \"...\" --json --download \"./out/{index}.{ext}\"\n\n# Local files: prefix the path with @ and the CLI uploads it and passes the hosted URL\nwavespeed run minimax/speech-2.6-turbo -i =@./local-file.png --json\n\n# Recover a result if the run was interrupted (the id is in the --json output)\nwavespeed show "},{"language":"bash","snippet":"npm install -g @wavespeed/cli\nwavespeed login # opens https://wavespeed.ai/accesskey and stores the key\nwavespeed status # confirms you are signed in"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: wavespeed-minimax-speech-26\ndescription: Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text.\nmetadata:\n author: wavespeedai\n version: \"2.0\"\n---\n\n# WaveSpeedAI MiniMax Speech 2.6 Turbo\n\nConvert text to speech using MiniMax Speech 2.6 Turbo via the WaveSpeed AI platform. Features ultra-human voice cloning, sub-250ms latency, 40+ language support, and emotion control.\n\n## Setup\n\nInstall the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:\n\n```bash\nnpm install -g @wavespeed/cli\nwavespeed login # opens https://wavespeed.ai/accesskey and stores the key\nwavespeed status # confirms you are signed in\n```\n\nFor CI or one-off shells, `WAVESPEED_API_KEY` in the environment also works.\n\nPrefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). It shares the CLI's stored login. Every example below maps one-to-one onto `run_model` with the same model id and input fields.\n\n## Quick Start\n\n```bash\nOUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \\\n -i text=\"Hello, welcome to WaveSpeed AI!\" \\\n -i voice_id=\"English_CalmWoman\" \\\n --json | jq -r '.outputs[0]')\n```\n\n## API Endpoint\n\n**Model ID:** `minimax/speech-2.6-turbo`\n\nConvert text to speech with configurable voice, emotion, speed, pitch, and audio format.\n\n### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `text` | string | Yes | -- | Text to convert to speech. Max 10,000 characters. Use `<#x#>` between words to insert pauses (0.01-99.99 seconds). |\n| `voice_id` | string | Yes | -- | Voice preset ID. See [Voice IDs](#voice-ids) below. |\n| `speed` | number | No | `1` | Speech speed. Range: 0.50-2.00 |\n| `volume` | number | No | `1` | Speech volume. Range: 0.10-10.00 |\n| `pitch` | number | No | `0` | Speech pitch. Range: -12 to 12 |\n| `emotion` | string | No | `happy` | Emotional tone. One of: `happy`, `sad`, `angry`, `fearful`, `disgusted`, `surprised`, `neutral` |\n| `english_normalization` | boolean | No | `false` | Improve English number reading normalization |\n| `sample_rate` | integer | No | -- | Sample rate in Hz. One of: `8000`, `16000`, `22050`, `24000`, `32000`, `44100` |\n| `bitrate` | integer | No | -- | Bitrate in bps. One of: `32000`, `64000`, `128000`, `256000` |\n| `channel` | string | No | -- | Audio channels. `1` (mono) or `2` (stereo) |\n| `format` | string | No | -- | Output format. One of: `mp3`, `wav`, `pcm`, `flac` |\n| `language_boost` | string | No | -- | Enhance recognition for a specific language. See [Supported Languages](#suppor"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn733k72mbe41a710dd1kfpg2s8257bs\",\n \"slug\": \"wavespeed-minimax-speech-26\",\n \"version\": \"2.0.1\",\n \"publishedAt\": 1788625803766\n}"},{"path":"skill-card.md","content":"## Description:\n\nConvert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI, with voice cloning, low-latency speech generation, multilingual support, emotion control, and voice presets.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[wavespeed](https://clawhub.ai/user/wavespeed)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent users use this skill to generate speech audio from text through WaveSpeed AI's MiniMax Speech 2.6 Turbo model. It helps configure voice, emotion, speed, pitch, language, and audio output settings.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Unpinned npm CLI or npx MCP setup can introduce normal package supply-chain risk.\n\nMitigation: Use pinned, reviewed package versions in sensitive environments.\n\nRisk: Text submitted for speech generation is sent to WaveSpeed AI.\n\nMitigation: Install and use the skill only when that service is acceptable for the text or files being processed.\n\nRisk: API keys may be exposed if pasted into chat.\n\nMitigation: Use the documented login flow or environment variable handling instead of sharing keys in chat.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/wavespeed/skills/wavespeed-minimax-speech-26)\n- [WaveSpeed MCP server](https://github.com/WaveSpeedAI/mcp-server)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands, Configuration instructions, API Calls]\n\n**Output Format:** [Markdown with inline bash commands and parameter guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [The skill guides text-to-speech requests that return generated audio URLs or downloaded audio files.]\n\n## Skill Version(s):\n\n2.0.1 (source: server release evidence)\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":"Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text. Skill: WaveSpeedAI MiniMax Speech 2.6 TTS Owner: wavespeed Summary: Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text. Tags: latest:2.0.1 Version history: v2.0.1 | 2026-09-05T16:30:03.766Z | user Moved to the @wavespeed organiza","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1113,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T15:48:26.887Z","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":"2026-10-11T15:48:26.887Z","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":"2026-10-11T20:57:05.230Z","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"}]}}}