{"id":"d7bc2385-c35a-4e04-ad93-4777beb633fb","entityType":"agent","slug":"clawhub-zrewolwerowanykaloryfer-deapi","name":"Deapi Github","canonicalUrl":"https://www.xpersona.co/agent/clawhub-zrewolwerowanykaloryfer-deapi","canonicalPath":"/agent/clawhub-zrewolwerowanykaloryfer-deapi","generatedAt":"2026-10-09T21:13:22.298Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"The cheapest AI media API on the market. Transcribe YouTube videos, generate images with Flux and Z-Image models, convert text to speech in 54+ voices across 8 languages, extract text with OCR, create videos, remove backgrounds, upscale images, apply style transfer - all through one unified API. Free $5 credit on signup - enough for hundreds of hours of transcription or thousands of generated images. Fraction of the cost of any alternative. Skill: Deapi Github Owner: zrewolwerowanykaloryfer Summary: The cheapest AI media API on the market. Transcribe YouTube videos, generate images with Flux and Z-Image models, convert text to speech in 54+ voices across 8 languages, extract text with OCR, create videos, remove backgrounds, upscale images, apply style transfer - all through one unified API. Free $5 credit on signup - enough for hundreds of hours of tran","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 876 downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn7d2s78ex44zmw98bdv67vsw180y6e0:deapi","sourceUrl":"https://clawhub.ai/zrewolwerowanykaloryfer/deapi","homepage":"https://clawhub.ai/zrewolwerowanykaloryfer/deapi","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/zrewolwerowanykaloryfer/deapi","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":59,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"The cheapest AI media API on the market. Transcribe YouTube videos, generate images with Flux and Z-Image models, convert text to speech in 54+ voices across 8 "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","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":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":876,"packageName":null,"latestVersion":"1.0.9","tractionLabel":"876 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-03-01T01:51:01.322Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-03-01T01:51:01.322Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-02T01:51:01.322Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.9","createdAt":"2026-02-13T18:24:49.020Z","changelog":"Reverted to 1.0.6","fileCount":3,"zipByteSize":6181},{"version":"1.0.8","createdAt":"2026-02-13T18:12:42.696Z","changelog":"Reverted 1.0.7 changes (untested LTX-2 update)","fileCount":13,"zipByteSize":15839},{"version":"1.0.7","createdAt":"2026-02-13T18:11:01.769Z","changelog":"Added LTX-2 19B video model","fileCount":null,"zipByteSize":null},{"version":"1.0.6","createdAt":"2026-02-11T13:57:37.783Z","changelog":"Reverted to placeholder paths per Testie review","fileCount":null,"zipByteSize":null},{"version":"1.0.5","createdAt":"2026-02-11T13:21:26.631Z","changelog":"Security fix: explicit /tmp/deapi_*.png paths instead of placeholders to pass virus scan","fileCount":null,"zipByteSize":null},{"version":"1.0.4","createdAt":"2026-02-11T13:08:41.979Z","changelog":"Fixed metadata format for ClawdHub requiredEnv detection (clawdbot.requires.env)","fileCount":null,"zipByteSize":null},{"version":"1.0.3","createdAt":"2026-02-11T12:25:01.912Z","changelog":"Fixed source URL to correct repository, updated author","fileCount":null,"zipByteSize":null},{"version":"1.0.2","createdAt":"2026-02-11T12:00:22.316Z","changelog":"Added homepage, source, author, license to metadata. Added privacy considerations (result_url accessibility, data handling). Added provenance links.","fileCount":null,"zipByteSize":null}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn7d2s78ex44zmw98bdv67vsw180y6e0:deapi","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","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-zrewolwerowanykaloryfer-deapi/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zrewolwerowanykaloryfer-deapi/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zrewolwerowanykaloryfer-deapi/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-zrewolwerowanykaloryfer-deapi/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-zrewolwerowanykaloryfer-deapi/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-zrewolwerowanykaloryfer-deapi/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T21:13:22.297Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zrewolwerowanykaloryfer-deapi/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zrewolwerowanykaloryfer-deapi/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zrewolwerowanykaloryfer-deapi/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zrewolwerowanykaloryfer-deapi/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":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: Deapi Github\n\nOwner: zrewolwerowanykaloryfer\n\nSummary: The cheapest AI media API on the market. Transcribe YouTube videos, generate images with Flux and Z-Image models, convert text to speech in 54+ voices across 8 languages, extract text with OCR, create videos, remove backgrounds, upscale images, apply style transfer - all through one unified API. Free $5 credit on signup - enough for hundreds of hours of transcription or thousands of generated images. Fraction of the cost of any alternative.\n\nTags: latest:1.0.9\n\nVersion history:\n\nv1.0.9 | 2026-02-13T18:24:49.020Z | user\n\nReverted to 1.0.6\n\nv1.0.8 | 2026-02-13T18:12:42.696Z | user\n\nReverted 1.0.7 changes (untested LTX-2 update)\n\nv1.0.7 | 2026-02-13T18:11:01.769Z | user\n\nAdded LTX-2 19B video model\n\nv1.0.6 | 2026-02-11T13:57:37.783Z | user\n\nReverted to placeholder paths per Testie review\n\nv1.0.5 | 2026-02-11T13:21:26.631Z | user\n\nSecurity fix: explicit /tmp/deapi_*.png paths instead of placeholders to pass virus scan\n\nv1.0.4 | 2026-02-11T13:08:41.979Z | user\n\nFixed metadata format for ClawdHub requiredEnv detection (clawdbot.requires.env)\n\nv1.0.3 | 2026-02-11T12:25:01.912Z | user\n\nFixed source URL to correct repository, updated author\n\nv1.0.2 | 2026-02-11T12:00:22.316Z | user\n\nAdded homepage, source, author, license to metadata. Added privacy considerations (result_url accessibility, data handling). Added provenance links.\n\nv1.0.1 | 2026-02-11T11:57:34.104Z | user\n\nSecurity improvements: replaced /tmp/ paths with placeholders, added security note explaining the skill documents legitimate API\n\nv1.0.0 | 2026-02-11T11:46:37.770Z | user\n\nInitial release - transcription (YouTube/audio/video), image generation (Flux, Z-Image), TTS (54+ voices, 8 languages), OCR, video generation, background removal, upscale (4x), style transfer, embeddings. 10-20x cheaper than alternatives.\n\nArchive index:\n\nArchive v1.0.9: 3 files, 6181 bytes\n\nFiles: README.md (2780b), SKILL.md (12905b), _meta.json (124b)\n\nFile v1.0.9:SKILL.md\n\n---\nname: deAPI AI Media Suite\ndescription: The cheapest AI media API on the market. Transcribe YouTube videos, generate images with Flux and Z-Image models, convert text to speech in 54+ voices across 8 languages, extract text with OCR, create videos, remove backgrounds, upscale images, apply style transfer - all through one unified API. Free $5 credit on signup - enough for hundreds of hours of transcription or thousands of generated images. Fraction of the cost of any alternative.\nhomepage: https://deapi.ai\nsource: https://github.com/zrewolwerowanykaloryfer/deapi-clawdbot-skill\nauthor: zrewolwerowanykaloryfer\nlicense: MIT\nrequiredEnv:\n  - DEAPI_API_KEY\nmetadata: {\"clawdbot\":{\"requires\":{\"env\":[\"DEAPI_API_KEY\"]}}}\ntags:\n  - media\n  - transcription\n  - image-generation\n  - tts\n  - ocr\n  - video\n  - audio\n  - embeddings\n---\n\n# deAPI Media Generation\n\nAI-powered media tools via decentralized GPU network. Get your API key at [deapi.ai](https://deapi.ai) (free $5 credit on signup).\n\n## Setup\n\n```bash\nexport DEAPI_API_KEY=your_api_key_here\n```\n\n## Available Functions\n\n| Function | Use when user wants to... |\n|----------|---------------------------|\n| Transcribe | Transcribe YouTube, Twitch, Kick, X videos, or audio files |\n| Generate Image | Generate images from text descriptions (Flux models) |\n| Generate Audio | Convert text to speech (TTS, 54+ voices, 8 languages) |\n| Generate Video | Create video from text or animate images |\n| OCR | Extract text from images |\n| Remove Background | Remove background from images |\n| Upscale | Upscale image resolution (2x/4x) |\n| Transform Image | Apply style transfer to images (multi-image support) |\n| Embeddings | Generate text embeddings for semantic search |\n| Check Balance | Check account balance |\n\n---\n\n## Async Pattern (Important!)\n\n**All deAPI requests are asynchronous.** Follow this pattern for every operation:\n\n### 1. Submit Request\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/{endpoint}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{...}'\n```\n\nResponse contains `request_id`.\n\n### 2. Poll Status (loop every 10 seconds)\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n### 3. Handle Status\n- `processing` → wait 10s, poll again\n- `done` → fetch result from `result_url`\n- `failed` → report error to user\n\n### Common Error Handling\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check DEAPI_API_KEY |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n\n---\n\n## Transcription (YouTube, Audio, Video)\n\n**Use when:** user wants to transcribe video from YouTube, X, Twitch, Kick or audio files.\n\n**Endpoints:**\n- Video (YouTube, mp4, webm): `vid2txt`\n- Audio (mp3, wav, m4a, flac, ogg): `aud2txt`\n\n**Request (video):**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/vid2txt\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"video_url\": \"{VIDEO_URL}\", \"include_ts\": true, \"model\": \"WhisperLargeV3\"}'\n```\n\n**Request (audio):**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/aud2txt\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"audio_url\": \"{AUDIO_URL}\", \"include_ts\": true, \"model\": \"WhisperLargeV3\"}'\n```\n\n**After polling:** Present transcription with timestamps in readable format.\n\n---\n\n## Image Generation (Flux)\n\n**Use when:** user wants to generate images from text descriptions.\n\n**Endpoint:** `txt2img`\n\n**Models:**\n| Model | API Name | Steps | Max Size | Notes |\n|-------|----------|-------|----------|-------|\n| Klein (default) | `Flux_2_Klein_4B_BF16` | 4 (fixed) | 1536px | Fastest, recommended |\n| Flux | `Flux1schnell` | 4-10 | 2048px | Higher resolution |\n| Turbo | `ZImageTurbo_INT8` | 4-10 | 1024px | Fastest inference |\n\n**Request:**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/txt2img\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"prompt\": \"{PROMPT}\",\n    \"model\": \"Flux_2_Klein_4B_BF16\",\n    \"width\": 1024,\n    \"height\": 1024,\n    \"steps\": 4,\n    \"seed\": {RANDOM_0_TO_999999}\n  }'\n```\n\n**Note:** Klein model does NOT support `guidance` parameter - omit it.\n\n---\n\n## Text-to-Speech (54+ Voices)\n\n**Use when:** user wants to convert text to speech.\n\n**Endpoint:** `txt2audio`\n\n**Popular Voices:**\n| Voice ID | Language | Description |\n|----------|----------|-------------|\n| `af_bella` | American EN | Warm, friendly (best quality) |\n| `af_heart` | American EN | Expressive, emotional |\n| `am_adam` | American EN | Deep, authoritative |\n| `bf_emma` | British EN | Elegant (best British) |\n| `jf_alpha` | Japanese | Natural Japanese female |\n| `zf_xiaobei` | Chinese | Mandarin female |\n| `ef_dora` | Spanish | Spanish female |\n| `ff_siwis` | French | French female (best quality) |\n\nVoice format: `{lang}{gender}_{name}` (e.g., `af_bella` = American Female Bella)\n\n**Request:**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/txt2audio\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"text\": \"{TEXT}\",\n    \"voice\": \"af_bella\",\n    \"model\": \"Kokoro\",\n    \"lang\": \"en-us\",\n    \"speed\": 1.0,\n    \"format\": \"mp3\",\n    \"sample_rate\": 24000\n  }'\n```\n\n**Parameters:** \n- `lang`: `en-us`, `en-gb`, `ja`, `zh`, `es`, `fr`, `hi`, `it`, `pt-br`\n- `speed`: 0.5-2.0\n- `format`: mp3/wav/flac/ogg\n- `sample_rate`: 22050/24000/44100/48000\n\n---\n\n## Video Generation\n\n**Use when:** user wants to generate video from text or animate an image.\n\n**Endpoints:**\n- Text-to-Video: `txt2video` (multipart/form-data)\n- Image-to-Video: `img2video` (multipart/form-data)\n\n**⚠️ IMPORTANT: Model-specific constraints for `Ltxv_13B_0_9_8_Distilled_FP8`:**\n- `guidance`: MUST be 0 (max value!)\n- `steps`: MUST be 1 (max value!)\n- `fps`: minimum 30\n\n**Request (text-to-video):**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/txt2video\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"prompt={PROMPT}\" \\\n  -F \"model=Ltxv_13B_0_9_8_Distilled_FP8\" \\\n  -F \"width=512\" \\\n  -F \"height=512\" \\\n  -F \"guidance=0\" \\\n  -F \"steps=1\" \\\n  -F \"frames=120\" \\\n  -F \"fps=30\" \\\n  -F \"seed={RANDOM_0_TO_999999}\"\n```\n\n**Parameters:**\n| Parameter | Required | Constraints | Description |\n|-----------|----------|-------------|-------------|\n| `prompt` | Yes | - | Video description |\n| `model` | Yes | - | `Ltxv_13B_0_9_8_Distilled_FP8` |\n| `width` | Yes | 256-768 | Video width (e.g., 512) |\n| `height` | Yes | 256-768 | Video height (e.g., 512) |\n| `guidance` | Yes | **max 0** | Must be 0 for this model |\n| `steps` | Yes | **max 1** | Must be 1 for this model |\n| `frames` | Yes | 30-300 | Number of frames |\n| `fps` | Yes | **min 30** | Frames per second |\n| `seed` | Yes | 0-999999 | Random seed |\n\n**Request (image-to-video):**\n```bash\n# Download image first if URL provided\ncurl -s -o {LOCAL_IMAGE_PATH} \"{IMAGE_URL}\"\n\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img2video\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"first_frame_image=@{LOCAL_IMAGE_PATH}\" \\\n  -F \"prompt=gentle movement, cinematic\" \\\n  -F \"model=Ltxv_13B_0_9_8_Distilled_FP8\" \\\n  -F \"width=512\" \\\n  -F \"height=512\" \\\n  -F \"guidance=0\" \\\n  -F \"steps=1\" \\\n  -F \"frames=120\" \\\n  -F \"fps=30\" \\\n  -F \"seed={RANDOM_0_TO_999999}\"\n```\n\n**Note:** Video generation can take 1-3 minutes.\n\n---\n\n## OCR (Image to Text)\n\n**Use when:** user wants to extract text from an image.\n\n**Endpoint:** `img2txt` (multipart/form-data)\n\n**Request:**\n```bash\n# Download image first if URL provided\ncurl -s -o {LOCAL_IMAGE_PATH} \"{IMAGE_URL}\"\n\n# Send OCR request\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img2txt\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"image=@{LOCAL_IMAGE_PATH}\" \\\n  -F \"model=Nanonets_Ocr_S_F16\"\n```\n\n---\n\n## Background Removal\n\n**Use when:** user wants to remove background from an image.\n\n**Endpoint:** `img-rmbg` (multipart/form-data)\n\n**Request:**\n```bash\n# Download image first if URL provided\ncurl -s -o {LOCAL_IMAGE_PATH} \"{IMAGE_URL}\"\n\n# Send remove-bg request\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img-rmbg\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"image=@{LOCAL_IMAGE_PATH}\" \\\n  -F \"model=Ben2\"\n```\n\n**Result:** PNG with transparent background.\n\n---\n\n## Image Upscale (2x/4x)\n\n**Use when:** user wants to upscale/enhance image resolution.\n\n**Endpoint:** `img-upscale` (multipart/form-data)\n\n**Models:**\n| Scale | Model |\n|-------|-------|\n| 2x | `RealESRGAN_x2` |\n| 4x | `RealESRGAN_x4` |\n\n**Request:**\n```bash\n# Download image first if URL provided\ncurl -s -o {LOCAL_IMAGE_PATH} \"{IMAGE_URL}\"\n\n# Send upscale request\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img-upscale\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"image=@{LOCAL_IMAGE_PATH}\" \\\n  -F \"model=RealESRGAN_x4\"\n```\n\n---\n\n## Image Transformation (Style Transfer)\n\n**Use when:** user wants to transform image style, combine images, or apply AI modifications.\n\n**Endpoint:** `img2img` (multipart/form-data)\n\n**Models:**\n| Model | API Name | Max Images | Guidance | Steps | Notes |\n|-------|----------|------------|----------|-------|-------|\n| Klein (default) | `Flux_2_Klein_4B_BF16` | 3 | N/A (ignore) | 4 (fixed) | Faster, multi-image |\n| Qwen | `QwenImageEdit_Plus_NF4` | 1 | 7.5 | 10-50 (default 20) | More control |\n\n**Request (Klein, supports up to 3 images):**\n```bash\n# Download images first\ncurl -s -o {LOCAL_IMAGE_1} \"{IMAGE_URL_1}\"\ncurl -s -o {LOCAL_IMAGE_2} \"{IMAGE_URL_2}\"  # optional\n\n# Send transform request (Klein - no guidance)\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img2img\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"image=@{LOCAL_IMAGE_1}\" \\\n  -F \"image=@{LOCAL_IMAGE_2}\" \\\n  -F \"prompt={STYLE_PROMPT}\" \\\n  -F \"model=Flux_2_Klein_4B_BF16\" \\\n  -F \"steps=4\" \\\n  -F \"seed={RANDOM_0_TO_999999}\"\n```\n\n**Request (Qwen, higher quality single image):**\n```bash\n# Download image first\ncurl -s -o {LOCAL_IMAGE_1} \"{IMAGE_URL}\"\n\n# Send transform request (Qwen - with guidance)\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img2img\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"image=@{LOCAL_IMAGE_1}\" \\\n  -F \"prompt={STYLE_PROMPT}\" \\\n  -F \"model=QwenImageEdit_Plus_NF4\" \\\n  -F \"guidance=7.5\" \\\n  -F \"steps=20\" \\\n  -F \"seed={RANDOM_0_TO_999999}\"\n```\n\n**Example prompts:** \"convert to watercolor painting\", \"anime style\", \"cyberpunk neon aesthetic\"\n\n---\n\n## Text Embeddings\n\n**Use when:** user needs embeddings for semantic search, clustering, or RAG.\n\n**Endpoint:** `txt2embedding`\n\n**Request:**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/txt2embedding\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"input\": \"{TEXT}\", \"model\": \"Bge_M3_FP16\"}'\n```\n\n**Result:** 1024-dimensional vector (BGE-M3, multilingual)\n\n---\n\n## Check Balance\n\n**Use when:** user wants to check remaining credits.\n\n**Request:**\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/balance\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n**Response:** `{ \"data\": { \"balance\": 4.25 } }`\n\n---\n\n## Pricing (Approximate)\n\n| Operation | Cost |\n|-----------|------|\n| Transcription | ~$0.02/hour |\n| Image Generation | ~$0.002/image |\n| TTS | ~$0.001/1000 chars |\n| Video Generation | ~$0.05/video |\n| OCR | ~$0.001/image |\n| Remove BG | ~$0.001/image |\n| Upscale | ~$0.002/image |\n| Embeddings | ~$0.0001/1000 tokens |\n\nFree $5 credit on signup at [deapi.ai](https://deapi.ai).\n\n---\n\n*Converted from [deapi-ai/claude-code-skills](https://github.com/deapi-ai/claude-code-skills) for Clawdbot/OpenClaw.*\n\n---\n\n## Security & Privacy Note\n\nThis skill provides documentation for the **deAPI.ai** REST API, a legitimate decentralized AI media service. \n\n**Security:**\n- All `curl` commands are **examples** showing how to call the API\n- Requests go to `api.deapi.ai` (official deAPI endpoint)\n- Local file paths (e.g., `{LOCAL_IMAGE_PATH}`) are placeholders - use any suitable temporary location\n- The skill itself does not execute code or download binaries\n- API key is required and must be set by user via `DEAPI_API_KEY` environment variable\n\n**Privacy considerations:**\n- Media URLs you submit (YouTube links, images) are sent to deapi.ai for processing\n- Generated results are returned via `result_url` which may be temporarily accessible via direct link\n- Results are stored on deAPI's infrastructure - review their privacy policy for retention details\n- Do not process sensitive/confidential media without understanding data handling\n\n**Provenance:**\n- Service provider: [deapi.ai](https://deapi.ai)\n- Original skill source: [github.com/deapi-ai/claude-code-skills](https://github.com/deapi-ai/claude-code-skills)\n- API documentation: [docs.deapi.ai](https://docs.deapi.ai)\n\nFile v1.0.9:README.md\n\n# deAPI AI Media Suite\n\n[![ClawHub](https://img.shields.io/badge/ClawHub-deapi-blue)](https://clawhub.ai/skills/deapi)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\n**The cheapest AI media API on the market** - now as a Clawdbot/OpenClaw skill.\n\nTranscribe YouTube videos, generate images, convert text to speech, extract text with OCR, create videos, remove backgrounds, and more - all through one unified API at a fraction of the cost.\n\n## 🚀 Features\n\n| Feature | Description |\n|---------|-------------|\n| 🎬 **Transcription** | YouTube, Twitch, Kick, X, audio/video files (Whisper) |\n| 🖼️ **Image Generation** | Flux and Z-Image models |\n| 🗣️ **Text-to-Speech** | 54+ voices across 8 languages |\n| 📝 **OCR** | Extract text from images |\n| 🎥 **Video Generation** | Text-to-video and image-to-video |\n| ✂️ **Background Removal** | Remove backgrounds from images |\n| 🔍 **Upscale** | 2x/4x image upscaling (RealESRGAN) |\n| 🎨 **Style Transfer** | Transform images with AI |\n| 🧮 **Embeddings** | Text embeddings for semantic search |\n\n## 📦 Installation\n\n```bash\nclawdhub install deapi\n```\n\n## ⚙️ Setup\n\n1. Get your API key at [deapi.ai](https://deapi.ai) (free $5 credit on signup)\n2. Set environment variable (or simply provide the API key to your agent when needed):\n   ```bash\n   export DEAPI_API_KEY=your_api_key_here\n   ```\n\n## 💰 Pricing\n\n- **Transcription:** ~$0.02/hour\n- **Image Generation:** ~$0.002/image  \n- **TTS:** ~$0.001/1000 chars\n- **Video Generation:** ~$0.05/video\n\nFree $5 credit = hundreds of hours of transcription or thousands of images!\n\n## 📖 Usage\n\nOnce installed, your Clawdbot agent automatically knows how to use deAPI. Just ask:\n\n- *\"Transcribe this YouTube video: [URL]\"*\n- *\"Generate an image of a robot in cyberpunk style\"*\n- *\"Convert this text to speech with a British accent\"*\n- *\"Extract text from this screenshot\"*\n- *\"Remove the background from this photo\"*\n- *\"Upscale this image 4x\"*\n\n## 🔒 Security & Privacy\n\n- All requests go to `api.deapi.ai` (official endpoint)\n- Media URLs you submit are sent to deAPI for processing\n- Results via `result_url` may be temporarily accessible\n- Review [deAPI's privacy policy](https://deapi.ai) for data handling details\n\n## 🙏 Credits\n\n- **API Provider:** [deAPI.ai](https://deapi.ai)\n- **Original Claude Code skill:** [deapi-ai/claude-code-skills](https://github.com/deapi-ai/claude-code-skills)\n- **Clawdbot conversion:** [@zrewolwerowanykaloryfer](https://github.com/zrewolwerowanykaloryfer)\n\n## 📄 License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n---\n\n**Links:** [ClawHub](https://clawhub.ai/skills/deapi) | [deAPI.ai](https://deapi.ai) | [API Docs](https://docs.deapi.ai)\n\nFile v1.0.9:_meta.json\n\n{\n  \"ownerId\": \"kn7d2s78ex44zmw98bdv67vsw180y6e0\",\n  \"slug\": \"deapi\",\n  \"version\": \"1.0.9\",\n  \"publishedAt\": 1771007089020\n}\n\nArchive v1.0.8: 13 files, 15839 bytes\n\nFiles: commands/deapi-balance.md (591b), commands/deapi-setup.md (3671b), commands/embed.md (2180b), commands/generate-audio.md (3397b), commands/generate-image.md (2687b), commands/generate-video.md (2346b), commands/ocr.md (2005b), commands/remove-bg.md (1972b), commands/transcribe.md (1900b), commands/transform-image.md (3468b), commands/upscale.md (2136b), SKILL.md (1830b), _meta.json (124b)\n\nFile v1.0.8:SKILL.md\n\n---\nname: deapi\ndescription: AI media generation via deAPI. Transcribe YouTube/audio/video, generate images from text, text-to-speech, OCR, remove backgrounds, upscale images, create videos, generate embeddings. 10-20x cheaper than OpenAI/Replicate.\nmetadata:\n  clawdbot:\n    config:\n      requiredEnv:\n        - DEAPI_API_KEY\ntags:\n  - media\n  - video\n  - image-generation\n  - transcription\n  - tts\n  - ocr\n---\n\n# deAPI Media Generation\n\nAI-powered media tools via decentralized GPU network.\n\n## Available Commands\n\n| Command | Use when user wants to... |\n|---------|---------------------------|\n| `/transcribe` | Transcribe YouTube, Twitch, Kick, X videos, or audio files |\n| `/generate-image` | Generate images from text descriptions |\n| `/generate-audio` | Convert text to speech (TTS) |\n| `/generate-video` | Create video from text or animate images |\n| `/ocr` | Extract text from images (OCR) |\n| `/remove-bg` | Remove background from images |\n| `/upscale` | Upscale image resolution (2x/4x) |\n| `/transform-image` | Apply style transfer to images |\n| `/embed` | Generate text embeddings for semantic search |\n| `/deapi-setup` | Configure result delivery (webhooks/websockets) for server apps |\n| `/deapi-balance` | Check account balance and remaining credits |\n\n## Quick Examples\n\n```\n/transcribe https://youtube.com/watch?v=...\n/generate-image a sunset over mountains\n/generate-audio \"Hello world\" --voice am_adam\n```\n\n## Setup\n\nRequires `DEAPI_API_KEY` environment variable:\n\n```bash\nexport DEAPI_API_KEY=your_key\n```\n\nGet your API key at [deapi.ai](https://deapi.ai) (free $5 credit).\n\n## API Pattern\n\nAll deAPI requests are async:\n1. Submit job → get `request_id`\n2. Poll status every 10s\n3. When `done` → fetch from `result_url`\n\nFor detailed API parameters, see [docs/api-reference.md](../docs/api-reference.md).\n\nFile v1.0.8:_meta.json\n\n{\n  \"ownerId\": \"kn7d2s78ex44zmw98bdv67vsw180y6e0\",\n  \"slug\": \"deapi\",\n  \"version\": \"1.0.8\",\n  \"publishedAt\": 1771006362696\n}\n\nFile v1.0.8:commands/deapi-balance.md\n\n---\nname: deapi-balance\ndescription: Check deAPI account balance\n---\n\n# deAPI Account Balance\n\n## Step 1: Check balance\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/balance\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n## Step 2: Present result\n\nResponse: `{ \"data\": { \"balance\": 4.25 } }`\n\nDisplay: **deAPI balance: {balance} credits**\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check if `$DEAPI_API_KEY` is set correctly |\n| 403 Forbidden | API key may be revoked, get a new one at deapi.ai |\n| Network error | Check internet connection |\n\nFile v1.0.8:commands/deapi-setup.md\n\n---\nname: deapi-setup\ndescription: Configure result delivery method for deAPI jobs (polling, webhooks, websockets)\n---\n\n# Result Delivery Setup\n\nConfigure how your application receives job results.\n\n## Step 1: Determine context\n\nAsk user about their use case:\n\n| Context | Recommended method |\n|---------|-------------------|\n| CLI tool, local script | **Polling** (default) |\n| Backend server, serverless | **Webhooks** |\n| Real-time UI, SPA | **WebSockets** |\n\n## Step 2: Configure based on method\n\n### Polling (default)\n\nNo configuration needed. Use `/request-status/{id}` endpoint.\nAlready built into all deAPI commands.\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\nPoll every 10 seconds until `status = \"done\"`.\n\n### Webhooks\n\nAdd `webhook_url` to any request:\n\n```json\n{\n  \"prompt\": \"...\",\n  \"webhook_url\": \"https://your-server.com/webhooks/deapi\"\n}\n```\n\n**Events received:**\n- `job.completed` - contains `result_url`\n- `job.failed` - contains `error_code`\n\n**Security:** Verify signature in `X-DeAPI-Signature` header (HMAC-SHA256).\n\nFull docs: https://docs.deapi.ai/execution-modes-and-integrations/webhooks\n\n### WebSockets\n\nConnect via Pusher protocol for real-time updates:\n\n| Setting | Value |\n|---------|-------|\n| Host | `soketi.deapi.ai:443` |\n| Channel | `private-client.{client_id}` |\n| Event | `request.status.updated` |\n\nIncludes live preview images during generation.\n\nFull docs: https://docs.deapi.ai/execution-modes-and-integrations/websockets\n\n## Step 3: Generate boilerplate\n\nBased on user's choice, generate starter code for their stack.\n\n**Webhook handler (Node.js/Express):**\n```javascript\napp.post('/webhooks/deapi', (req, res) => {\n  const signature = req.headers['x-deapi-signature'];\n  // Verify signature with your webhook secret\n\n  const { event, request_id, result_url, error } = req.body;\n\n  if (event === 'job.completed') {\n    // Process result from result_url\n  } else if (event === 'job.failed') {\n    // Handle error\n  }\n\n  res.status(200).send('OK');\n});\n```\n\n**Webhook handler (Python/FastAPI):**\n```python\nfrom fastapi import FastAPI, Request, Header\n\napp = FastAPI()\n\n@app.post(\"/webhooks/deapi\")\nasync def deapi_webhook(\n    request: Request,\n    x_deapi_signature: str = Header(None)\n):\n    # Verify signature with your webhook secret\n    body = await request.json()\n\n    if body[\"event\"] == \"job.completed\":\n        result_url = body[\"result_url\"]\n        # Process result\n    elif body[\"event\"] == \"job.failed\":\n        error = body[\"error\"]\n        # Handle error\n\n    return {\"status\": \"ok\"}\n```\n\n**WebSocket client (JavaScript):**\n```javascript\nimport Pusher from 'pusher-js';\n\nconst pusher = new Pusher('your-app-key', {\n  wsHost: 'soketi.deapi.ai',\n  wsPort: 443,\n  forceTLS: true,\n  disableStats: true,\n  enabledTransports: ['ws', 'wss']\n});\n\nconst channel = pusher.subscribe(`private-client.${clientId}`);\n\nchannel.bind('request.status.updated', (data) => {\n  if (data.status === 'done') {\n    // Fetch result from data.result_url\n  }\n});\n```\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| Webhook timeout | Retry with exponential backoff (1s, 2s, 4s) |\n| Invalid signature | Verify webhook secret matches dashboard config |\n| WebSocket disconnect | Reconnect with backoff, resubscribe to channel |\n| 401 on polling | Check `DEAPI_API_KEY` is valid |\n| Missing `result_url` | Job may still be processing, continue polling |\n\n## When to suggest this skill\n\nProactively suggest `/deapi-setup` when user mentions:\n- Building a web app with deAPI\n- Server-side integration\n- Real-time UI updates\n- Production deployment\n\nFile v1.0.8:commands/embed.md\n\n---\nname: embed\ndescription: Generate text embeddings for semantic search and similarity\nargument-hint: <text>\n---\n\n# Text Embeddings via deAPI\n\nGenerate embeddings for: **$ARGUMENTS**\n\n## Step 1: Validate input\n\nVerify `$ARGUMENTS` contains text to embed:\n- Text should not be empty\n- Maximum recommended length: 8192 tokens\n- For longer texts, consider chunking\n\n## Step 2: Send request\n\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/txt2embedding\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"input\": \"$ARGUMENTS\",\n    \"model\": \"Bge_M3_FP16\"\n  }'\n```\n\n**Model info:**\n| Model | Dimensions | Best for |\n|-------|------------|----------|\n| `Bge_M3_FP16` | 1024 | High accuracy, semantic search, multilingual |\n\n## Step 3: Poll status (feedback loop)\n\nExtract `request_id` from response, then poll every 10 seconds:\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n**Status handling:**\n- `processing` → wait 10s, poll again\n- `done` → proceed to Step 4\n- `failed` → report error message to user, STOP\n\n## Step 4: Fetch and present result\n\nWhen `status = \"done\"`:\n1. Get embedding vector from response\n2. Show vector dimensions and sample values\n3. Offer to save or use the embedding\n\n**Output format:**\n```json\n{\n  \"embedding\": [0.123, -0.456, 0.789, ...],\n  \"dimensions\": 1024,\n  \"model\": \"Bge_M3_FP16\"\n}\n```\n\n## Step 5: Offer follow-up\n\nAsk user:\n- \"Would you like to embed more text for comparison?\"\n- \"Should I calculate similarity between embeddings?\"\n- \"Would you like to save these embeddings to a file?\"\n\n## Use cases\n\n- **Semantic search**: Find similar documents\n- **Clustering**: Group related content\n- **RAG**: Retrieval-augmented generation\n- **Recommendations**: Content similarity\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check if `$DEAPI_API_KEY` is set correctly |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n| Empty text | Ask user to provide text to embed |\n| Text too long | Suggest chunking into smaller segments |\n\nFile v1.0.8:commands/generate-audio.md\n\n---\nname: generate-audio\ndescription: Convert text to speech using 54+ AI voices in 8 languages\nargument-hint: <text> [--voice af_bella]\n---\n\n# Text-to-Speech via deAPI\n\nGenerate audio from text: **$ARGUMENTS**\n\n## Step 1: Parse arguments\n\nExtract from `$ARGUMENTS`:\n- `text`: The text to convert to speech (required)\n- `--voice`: Voice ID (default: `af_bella`)\n\n**54+ voices in 8 languages.** Voice ID format: `{lang}{gender}_{name}`\n- Lang: `a`=American, `b`=British, `j`=Japanese, `z`=Chinese, `e`=Spanish, `f`=French, `h`=Hindi, `i`=Italian, `p`=Portuguese\n- Gender: `f`=female, `m`=male\n\n**Popular voices:**\n| Voice ID | Language | Description |\n|----------|----------|-------------|\n| `af_bella` | American EN | Warm, friendly (best quality) |\n| `af_heart` | American EN | Expressive, emotional |\n| `af_nicole` | American EN | Professional |\n| `af_sarah` | American EN | Casual |\n| `am_adam` | American EN | Deep, authoritative |\n| `am_michael` | American EN | Energetic |\n| `bf_emma` | British EN | Elegant (best British) |\n| `bf_isabella` | British EN | Refined |\n| `bm_george` | British EN | Sophisticated |\n| `jf_alpha` | Japanese | Natural Japanese female |\n| `zf_xiaobei` | Chinese | Mandarin female |\n| `ef_dora` | Spanish | Spanish female |\n| `ff_siwis` | French | French female (best quality) |\n| `hf_alpha` | Hindi | Hindi female |\n| `if_sara` | Italian | Italian female |\n| `pf_dora` | Portuguese | Brazilian Portuguese female |\n\nFull list: [Kokoro VOICES.md](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md)\n\n## Step 2: Send request\n\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/txt2audio\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"text\": \"{text}\",\n    \"voice\": \"{voice}\",\n    \"model\": \"Kokoro\",\n    \"lang\": \"{lang_code}\",\n    \"speed\": 1.0,\n    \"format\": \"mp3\",\n    \"sample_rate\": 24000\n  }'\n```\n\n**Parameters:**\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `lang` | auto from voice | Language code: `en-us`, `en-gb`, `ja`, `zh`, `es`, `fr`, `hi`, `it`, `pt-br` |\n| `speed` | `1.0` | Speech speed (0.5-2.0) |\n| `format` | `mp3` | Output format: `mp3`, `wav`, `flac`, `ogg` |\n| `sample_rate` | `24000` | Sample rate: `22050`, `24000`, `44100`, `48000` |\n\n## Step 3: Poll status (feedback loop)\n\nExtract `request_id` from response, then poll every 10 seconds:\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n**Status handling:**\n- `processing` → wait 10s, poll again\n- `done` → proceed to Step 4\n- `failed` → report error message to user, STOP\n\n## Step 4: Fetch and present result\n\nWhen `status = \"done\"`:\n1. Get audio URL from `result_url`\n2. Provide download link to user\n3. Show audio duration if available\n\n## Step 5: Offer follow-up\n\nAsk user:\n- \"Would you like to try a different voice?\"\n- \"Should I generate this in another language?\"\n- \"Would you like to adjust the text?\"\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check if `$DEAPI_API_KEY` is set correctly |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n| Empty text | Ask user to provide text to convert |\n| Invalid voice | Show available voices, ask user to choose |\n| Text too long | Suggest splitting into smaller segments |\n\nFile v1.0.8:commands/generate-image.md\n\n---\nname: generate-image\ndescription: Generate images from text prompts using Flux Klein, Flux Schnell, or ZImageTurbo models\nargument-hint: <prompt> [--model klein|flux|turbo] [--size 512|768|1024]\n---\n\n# Image Generation via deAPI\n\nGenerate image from prompt: **$ARGUMENTS**\n\n## Step 1: Parse arguments\n\nExtract from `$ARGUMENTS`:\n- `prompt`: The text description (required)\n- `--model`: `klein` (default, recommended), `flux` (higher max resolution), or `turbo` (fastest)\n- `--size`: `512`, `768`, or `1024` (default: 1024). Klein supports up to 1536.\n\n## Step 2: Send request\n\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/txt2img\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"prompt\": \"{prompt}\",\n    \"model\": \"{model_name}\",\n    \"width\": {size},\n    \"height\": {size},\n    \"steps\": {steps},\n    \"seed\": {random_seed}\n  }'\n```\n\n**Model mapping:**\n| User flag | API model name | Steps | Max size | Info |\n|-----------|----------------|-------|----------|------|\n| `klein` (default) | `Flux_2_Klein_4B_BF16` | 4 (fixed) | 1536 | Recommended, txt2img + img2img, multi-image |\n| `flux` | `Flux1schnell` | 4-10 (default: 4) | 2048 | Higher max resolution |\n| `turbo` | `ZImageTurbo_INT8` | 4-10 (default: 4) | 1024 | Fastest |\n\n**Klein model limits:**\n- Resolution: 256-1536px (step: 16)\n- Steps: 4 (fixed)\n- Guidance: not supported (parameter ignored)\n\n**Important:** Generate a random seed (0-999999) for each request.\n\n**Note:** Klein does not support `guidance` parameter - omit it or it will be ignored.\n\n## Step 3: Poll status (feedback loop)\n\nExtract `request_id` from response, then poll every 10 seconds:\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n**Status handling:**\n- `processing` → wait 10s, poll again\n- `done` → proceed to Step 4\n- `failed` → report error message to user, STOP\n\n## Step 4: Fetch and present result\n\nWhen `status = \"done\"`:\n1. Get image URL from `result_url`\n2. Display/download the generated image\n3. Show the image to the user\n\n## Step 5: Offer follow-up\n\nAsk user:\n- \"Would you like variations with a modified prompt?\"\n- \"Should I upscale this image?\"\n- \"Would you like to transform this with additional images?\" (Klein supports up to 3 input images in img2img)\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check if `$DEAPI_API_KEY` is set correctly |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n| Empty prompt | Ask user to provide a description |\n| NSFW rejected | Inform user, suggest alternative prompt |\n\nFile v1.0.8:commands/generate-video.md\n\n---\nname: generate-video\ndescription: Generate videos from text prompts or animate images\nargument-hint: <prompt-or-image-url> [--mode text|image]\n---\n\n# Video Generation via deAPI\n\nGenerate video: **$ARGUMENTS**\n\n## Step 1: Determine mode and parse arguments\n\n**Auto-detect mode:**\n- If `$ARGUMENTS` starts with `http` → Image-to-Video (`img2video`)\n- Otherwise → Text-to-Video (`txt2video`)\n\n**Override with `--mode`:**\n- `--mode text`: Force text-to-video\n- `--mode image`: Force image-to-video\n\n## Step 2: Send request\n\n**For Text-to-Video:**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/txt2video\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"prompt\": \"{prompt}\",\n    \"duration\": 4,\n    \"fps\": 24,\n    \"model\": \"Ltxv_13B_0_9_8_Distilled_FP8\"\n  }'\n```\n\n**For Image-to-Video (animation):**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img2video\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"image_url\": \"{image_url}\",\n    \"motion_prompt\": \"gentle movement, cinematic\",\n    \"duration\": 4,\n    \"fps\": 24\n  }'\n```\n\n## Step 3: Poll status (feedback loop)\n\nExtract `request_id` from response, then poll every 10 seconds:\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n**Status handling:**\n- `processing` → wait 10s, poll again (video generation can take 1-3 minutes)\n- `done` → proceed to Step 4\n- `failed` → report error message to user, STOP\n\n## Step 4: Fetch and present result\n\nWhen `status = \"done\"`:\n1. Get video URL from `result_url`\n2. Provide download link to user\n3. Show video details (duration, resolution)\n\n## Step 5: Offer follow-up\n\nAsk user:\n- \"Would you like to generate a longer version?\"\n- \"Should I try a different motion style?\"\n- \"Would you like to generate more variations?\"\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check if `$DEAPI_API_KEY` is set correctly |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n| Empty prompt | Ask user to provide a description |\n| Invalid image URL | Verify URL is accessible and points to an image |\n| Timeout (>5min) | Inform user, video generation is resource-intensive |\n\nFile v1.0.8:commands/ocr.md\n\n---\nname: ocr\ndescription: Extract text from images using AI-powered OCR\nargument-hint: <image-url>\n---\n\n# OCR (Image to Text) via deAPI\n\nExtract text from image: **$ARGUMENTS**\n\n## Step 1: Validate input\n\nVerify `$ARGUMENTS` is a valid image file path or URL:\n- Supported formats: `.png`, `.jpg`, `.jpeg`, `.webp`, `.gif`, `.bmp`\n- If URL provided, download the file first\n\n## Step 2: Send request\n\n**Note:** This endpoint requires `multipart/form-data` with file upload.\n\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img2txt\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"image=@{local_file_path}\" \\\n  -F \"model=Nanonets_Ocr_S_F16\"\n```\n\nIf user provides a URL, first download the image:\n```bash\ncurl -s -o /tmp/ocr_image.png \"{image_url}\"\n```\nThen use `/tmp/ocr_image.png` as the file path.\n\n## Step 3: Poll status (feedback loop)\n\nExtract `request_id` from response, then poll every 10 seconds:\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n**Status handling:**\n- `processing` → wait 10s, poll again\n- `done` → proceed to Step 4\n- `failed` → report error message to user, STOP\n\n## Step 4: Fetch and present result\n\nWhen `status = \"done\"`:\n1. Get extracted text from response or `result_url`\n2. Present text in clean, formatted manner\n3. Preserve original structure (paragraphs, lists) where possible\n\n## Step 5: Offer follow-up\n\nAsk user:\n- \"Would you like me to summarize this text?\"\n- \"Should I translate this to another language?\"\n- \"Would you like to extract text from another image?\"\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check if `$DEAPI_API_KEY` is set correctly |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n| Invalid URL | Ask user to verify the image URL |\n| No text found | Inform user the image may not contain readable text |\n| Image too large | Suggest resizing or cropping the image |\n\nFile v1.0.8:commands/remove-bg.md\n\n---\nname: remove-bg\ndescription: Remove background from images using AI\nargument-hint: <image-url>\n---\n\n# Background Removal via deAPI\n\nRemove background from image: **$ARGUMENTS**\n\n## Step 1: Validate input\n\nVerify `$ARGUMENTS` is a valid image file path or URL:\n- Supported formats: `.png`, `.jpg`, `.jpeg`, `.webp`\n- If URL provided, download the file first\n- Best results with clear subject/foreground\n\n## Step 2: Send request\n\n**Note:** This endpoint requires `multipart/form-data` with file upload.\n\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img-rmbg\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"image=@{local_file_path}\" \\\n  -F \"model=Ben2\"\n```\n\nIf user provides a URL, first download the image:\n```bash\ncurl -s -o /tmp/rmbg_image.png \"{image_url}\"\n```\nThen use `/tmp/rmbg_image.png` as the file path.\n\n## Step 3: Poll status (feedback loop)\n\nExtract `request_id` from response, then poll every 10 seconds:\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n**Status handling:**\n- `processing` → wait 10s, poll again\n- `done` → proceed to Step 4\n- `failed` → report error message to user, STOP\n\n## Step 4: Fetch and present result\n\nWhen `status = \"done\"`:\n1. Get processed image URL from `result_url`\n2. Result is PNG with transparent background\n3. Provide download link to user\n\n## Step 5: Offer follow-up\n\nAsk user:\n- \"Would you like to add a new background color?\"\n- \"Should I process another image?\"\n- \"Would you like to resize the result?\"\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check if `$DEAPI_API_KEY` is set correctly |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n| Invalid URL | Ask user to verify the image URL |\n| No subject detected | Image may lack clear foreground; suggest different image |\n| Image too large | Suggest resizing before processing |\n\nFile v1.0.8:commands/transcribe.md\n\n---\nname: transcribe\ndescription: Transcribes video/audio from URLs (YouTube, X, mp3, mp4, wav) using Whisper AI\nargument-hint: <url>\n---\n\n# Transcription via deAPI\n\nTranscribe media from URL: **$ARGUMENTS**\n\n## Step 1: Determine endpoint\n\n| URL type | Endpoint |\n|----------|----------|\n| `.mp3`, `.wav`, `.m4a`, `.flac`, `.ogg` | `aud2txt` |\n| YouTube, X, `.mp4`, `.webm`, other video | `vid2txt` |\n\n## Step 2: Send request\n\n**For video:**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/vid2txt\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"video_url\": \"$ARGUMENTS\", \"include_ts\": true, \"model\": \"WhisperLargeV3\"}'\n```\n\n**For audio:**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/aud2txt\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"audio_url\": \"$ARGUMENTS\", \"include_ts\": true, \"model\": \"WhisperLargeV3\"}'\n```\n\n## Step 3: Poll status (feedback loop)\n\nExtract `request_id` from response, then poll every 10 seconds:\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n**Status handling:**\n- `processing` → wait 10s, poll again\n- `done` → proceed to Step 4\n- `failed` → report error message to user, STOP\n\n## Step 4: Fetch and present result\n\nWhen `status = \"done\"`, fetch content from `result_url` and present transcription in readable format with timestamps.\n\n## Step 5: Offer follow-up\n\nAsk user: \"Would you like me to summarize the main points?\"\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check if `$DEAPI_API_KEY` is set correctly |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n| Invalid URL | Ask user to verify the URL format |\n| Timeout (>5min) | Inform user, suggest trying shorter content |\n\nFile v1.0.8:commands/transform-image.md\n\n---\nname: transform-image\ndescription: Transform images with style transfer and AI modifications\nargument-hint: <image-url> <style-prompt> [--model klein|qwen]\n---\n\n# Image Transformation via deAPI\n\nTransform image: **$ARGUMENTS**\n\n## Step 1: Parse arguments\n\nExtract from `$ARGUMENTS`:\n- `image_url`: URL(s) to source image(s) - Klein supports up to 3 images (required)\n- `style_prompt`: Description of desired transformation (required)\n- `--model`: `klein` (default, faster, multi-image) or `qwen` (higher steps, more control)\n\n**Example style prompts:**\n- \"convert to watercolor painting\"\n- \"make it look like a vintage photograph\"\n- \"transform into anime style\"\n- \"add cyberpunk neon aesthetic\"\n- \"combine these images into one scene\" (multi-image with Klein)\n\n## Step 2: Send request\n\n**Note:** This endpoint requires `multipart/form-data` with file upload.\n\nIf user provides URL(s), first download the image(s):\n```bash\ncurl -s -o /tmp/transform_image1.png \"{image_url_1}\"\ncurl -s -o /tmp/transform_image2.png \"{image_url_2}\"  # optional\ncurl -s -o /tmp/transform_image3.png \"{image_url_3}\"  # optional\n```\n\nThen send the transformation request:\n\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/img2img\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -F \"image=@{local_file_path_1}\" \\\n  -F \"image=@{local_file_path_2}\" \\\n  -F \"image=@{local_file_path_3}\" \\\n  -F \"prompt={style_prompt}\" \\\n  -F \"model={model_name}\" \\\n  -F \"guidance={guidance}\" \\\n  -F \"steps={steps}\" \\\n  -F \"seed={random_seed}\"\n```\n\n**Model mapping:**\n| User flag | API model name | Steps | Guidance | Max images | Info |\n|-----------|----------------|-------|----------|------------|------|\n| `klein` (default) | `Flux_2_Klein_4B_BF16` | 4 (fixed) | ignored | 3 | Faster, multi-image support |\n| `qwen` | `QwenImageEdit_Plus_NF4` | 10-50 (default: 20) | 7.5 | 1 | More control, higher fidelity |\n\n**Klein model limits:**\n- Resolution: 256-1536px (step: 16)\n- Steps: 4 (fixed)\n- Guidance: not supported\n- Max input images: 3\n\n**Parameters:**\n| Parameter | Klein | Qwen | Description |\n|-----------|-------|------|-------------|\n| `guidance` | ignored | 7.5 | Prompt adherence (1-20) |\n| `steps` | 4 (fixed) | 20 | Inference steps |\n| `seed` | random | random | For reproducibility (0-999999) |\n\n## Step 3: Poll status (feedback loop)\n\nExtract `request_id` from response, then poll every 10 seconds:\n\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n**Status handling:**\n- `processing` → wait 10s, poll again\n- `done` → proceed to Step 4\n- `failed` → report error message to user, STOP\n\n## Step 4: Fetch and present result\n\nWhen `status = \"done\"`:\n1. Get transformed image URL from `result_url`\n2. Display before/after comparison if possible\n3. Provide download link to user\n\n## Step 5: Offer follow-up\n\nAsk user:\n- \"Would you like to try a different style?\"\n- \"Should I add more input images?\" (Klein only, up to 3)\n- \"Would you like to upscale the result?\"\n\n## Error handling\n\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check if `$DEAPI_API_KEY` is set correctly |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n| Invalid URL | Ask user to verify the image URL |\n| Missing prompt | Ask user to describe desired transformation |\n| Too many images | Klein max 3, Qwen max 1 |\n| NSFW rejected | Inform user, suggest alternative style |","readmeExcerpt":"Skill: Deapi Github Owner: zrewolwerowanykaloryfer Summary: The cheapest AI media API on the market. Transcribe YouTube videos, generate images with Flux and Z-Image models, convert text to speech in 54+ voices across 8 languages, extract text with OCR, create videos, remove backgrounds, upscale images, apply style transfer - all through one unified API. Free $5 credit on signup - enough for hundreds of hours of tran","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"export DEAPI_API_KEY=your_api_key_here"},{"language":"bash","snippet":"curl -s -X POST \"https://api.deapi.ai/api/v1/client/{endpoint}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{...}'"},{"language":"bash","snippet":"curl -s -X POST \"https://api.deapi.ai/api/v1/client/{endpoint}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{...}'"},{"language":"bash","snippet":"curl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\""},{"language":"bash","snippet":"curl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\""},{"language":"bash","snippet":"curl -s -X POST \"https://api.deapi.ai/api/v1/client/vid2txt\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"video_url\": \"{VIDEO_URL}\", \"include_ts\": true, \"model\": \"WhisperLargeV3\"}'"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: deAPI AI Media Suite\ndescription: The cheapest AI media API on the market. Transcribe YouTube videos, generate images with Flux and Z-Image models, convert text to speech in 54+ voices across 8 languages, extract text with OCR, create videos, remove backgrounds, upscale images, apply style transfer - all through one unified API. Free $5 credit on signup - enough for hundreds of hours of transcription or thousands of generated images. Fraction of the cost of any alternative.\nhomepage: https://deapi.ai\nsource: https://github.com/zrewolwerowanykaloryfer/deapi-clawdbot-skill\nauthor: zrewolwerowanykaloryfer\nlicense: MIT\nrequiredEnv:\n  - DEAPI_API_KEY\nmetadata: {\"clawdbot\":{\"requires\":{\"env\":[\"DEAPI_API_KEY\"]}}}\ntags:\n  - media\n  - transcription\n  - image-generation\n  - tts\n  - ocr\n  - video\n  - audio\n  - embeddings\n---\n\n# deAPI Media Generation\n\nAI-powered media tools via decentralized GPU network. Get your API key at [deapi.ai](https://deapi.ai) (free $5 credit on signup).\n\n## Setup\n\n```bash\nexport DEAPI_API_KEY=your_api_key_here\n```\n\n## Available Functions\n\n| Function | Use when user wants to... |\n|----------|---------------------------|\n| Transcribe | Transcribe YouTube, Twitch, Kick, X videos, or audio files |\n| Generate Image | Generate images from text descriptions (Flux models) |\n| Generate Audio | Convert text to speech (TTS, 54+ voices, 8 languages) |\n| Generate Video | Create video from text or animate images |\n| OCR | Extract text from images |\n| Remove Background | Remove background from images |\n| Upscale | Upscale image resolution (2x/4x) |\n| Transform Image | Apply style transfer to images (multi-image support) |\n| Embeddings | Generate text embeddings for semantic search |\n| Check Balance | Check account balance |\n\n---\n\n## Async Pattern (Important!)\n\n**All deAPI requests are asynchronous.** Follow this pattern for every operation:\n\n### 1. Submit Request\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/{endpoint}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{...}'\n```\n\nResponse contains `request_id`.\n\n### 2. Poll Status (loop every 10 seconds)\n```bash\ncurl -s \"https://api.deapi.ai/api/v1/client/request-status/{request_id}\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KEY\"\n```\n\n### 3. Handle Status\n- `processing` → wait 10s, poll again\n- `done` → fetch result from `result_url`\n- `failed` → report error to user\n\n### Common Error Handling\n| Error | Action |\n|-------|--------|\n| 401 Unauthorized | Check DEAPI_API_KEY |\n| 429 Rate Limited | Wait 60s and retry |\n| 500 Server Error | Wait 30s and retry once |\n\n---\n\n## Transcription (YouTube, Audio, Video)\n\n**Use when:** user wants to transcribe video from YouTube, X, Twitch, Kick or audio files.\n\n**Endpoints:**\n- Video (YouTube, mp4, webm): `vid2txt`\n- Audio (mp3, wav, m4a, flac, ogg): `aud2txt`\n\n**Request (video):**\n```bash\ncurl -s -X POST \"https://api.deapi.ai/api/v1/client/vid2txt\" \\\n  -H \"Authorization: Bearer $DEAPI_API_KE"},{"path":"README.md","content":"# deAPI AI Media Suite\n\n[![ClawHub](https://img.shields.io/badge/ClawHub-deapi-blue)](https://clawhub.ai/skills/deapi)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\n**The cheapest AI media API on the market** - now as a Clawdbot/OpenClaw skill.\n\nTranscribe YouTube videos, generate images, convert text to speech, extract text with OCR, create videos, remove backgrounds, and more - all through one unified API at a fraction of the cost.\n\n## 🚀 Features\n\n| Feature | Description |\n|---------|-------------|\n| 🎬 **Transcription** | YouTube, Twitch, Kick, X, audio/video files (Whisper) |\n| 🖼️ **Image Generation** | Flux and Z-Image models |\n| 🗣️ **Text-to-Speech** | 54+ voices across 8 languages |\n| 📝 **OCR** | Extract text from images |\n| 🎥 **Video Generation** | Text-to-video and image-to-video |\n| ✂️ **Background Removal** | Remove backgrounds from images |\n| 🔍 **Upscale** | 2x/4x image upscaling (RealESRGAN) |\n| 🎨 **Style Transfer** | Transform images with AI |\n| 🧮 **Embeddings** | Text embeddings for semantic search |\n\n## 📦 Installation\n\n```bash\nclawdhub install deapi\n```\n\n## ⚙️ Setup\n\n1. Get your API key at [deapi.ai](https://deapi.ai) (free $5 credit on signup)\n2. Set environment variable (or simply provide the API key to your agent when needed):\n   ```bash\n   export DEAPI_API_KEY=your_api_key_here\n   ```\n\n## 💰 Pricing\n\n- **Transcription:** ~$0.02/hour\n- **Image Generation:** ~$0.002/image  \n- **TTS:** ~$0.001/1000 chars\n- **Video Generation:** ~$0.05/video\n\nFree $5 credit = hundreds of hours of transcription or thousands of images!\n\n## 📖 Usage\n\nOnce installed, your Clawdbot agent automatically knows how to use deAPI. Just ask:\n\n- *\"Transcribe this YouTube video: [URL]\"*\n- *\"Generate an image of a robot in cyberpunk style\"*\n- *\"Convert this text to speech with a British accent\"*\n- *\"Extract text from this screenshot\"*\n- *\"Remove the background from this photo\"*\n- *\"Upscale this image 4x\"*\n\n## 🔒 Security & Privacy\n\n- All requests go to `api.deapi.ai` (official endpoint)\n- Media URLs you submit are sent to deAPI for processing\n- Results via `result_url` may be temporarily accessible\n- Review [deAPI's privacy policy](https://deapi.ai) for data handling details\n\n## 🙏 Credits\n\n- **API Provider:** [deAPI.ai](https://deapi.ai)\n- **Original Claude Code skill:** [deapi-ai/claude-code-skills](https://github.com/deapi-ai/claude-code-skills)\n- **Clawdbot conversion:** [@zrewolwerowanykaloryfer](https://github.com/zrewolwerowanykaloryfer)\n\n## 📄 License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n---\n\n**Links:** [ClawHub](https://clawhub.ai/skills/deapi) | [deAPI.ai](https://deapi.ai) | [API Docs](https://docs.deapi.ai)"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7d2s78ex44zmw98bdv67vsw180y6e0\",\n  \"slug\": \"deapi\",\n  \"version\": \"1.0.9\",\n  \"publishedAt\": 1771007089020\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"The cheapest AI media API on the market. Transcribe YouTube videos, generate images with Flux and Z-Image models, convert text to speech in 54+ voices across 8 languages, extract text with OCR, create videos, remove backgrounds, upscale images, apply style transfer - all through one unified API. Free $5 credit on signup - enough for hundreds of hours of transcription or thousands of generated images. Fraction of the cost of any alternative. Skill: Deapi Github Owner: zrewolwerowanykaloryfer Summary: The cheapest AI media API on the market. Transcribe YouTube videos, generate images with Flux and Z-Image models, convert text to speech in 54+ voices across 8 languages, extract text with OCR, create videos, remove backgrounds, upscale images, apply style transfer - all through one unified API. Free $5 credit on signup - enough for hundreds of hours of tran","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":996,"uniquenessScore":50,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","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":"2026-04-15T00:45:39.800Z","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":"2026-10-09T21:13:22.298Z","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"}]}}}