{ "schemaVersion": "1.0", "item": { "slug": "whisper-stt", "name": "Whisper STT", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/nickylin/whisper-stt", "canonicalUrl": "https://clawhub.ai/nickylin/whisper-stt", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/whisper-stt", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=whisper-stt", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/demo.sh", "scripts/transcribe.py" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/whisper-stt" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/whisper-stt", "agentPageUrl": "https://openagent3.xyz/skills/whisper-stt/agent", "manifestUrl": "https://openagent3.xyz/skills/whisper-stt/agent.json", "briefUrl": "https://openagent3.xyz/skills/whisper-stt/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Whisper STT Skill", "body": "Free, local speech-to-text using OpenAI Whisper." }, { "title": "Prerequisites", "body": "Install dependencies (one-time setup):\n\npip install openai-whisper torch\n\nOptional: Install ffmpeg for broader format support:\n\nmacOS: brew install ffmpeg\nUbuntu: sudo apt install ffmpeg" }, { "title": "Transcribe an audio file", "body": "python ~/.openclaw/skills/whisper-stt/scripts/transcribe.py " }, { "title": "Options", "body": "OptionDescription--modelModel size: tiny, base, small, medium, large, large-v3-turbo (default: base)--language, -lLanguage code: zh, en, ja, etc. (auto-detect if not specified)--output, -oOutput format: json, txt, srt, vtt (default: json)" }, { "title": "Examples", "body": "Chinese audio to text:\n\npython ~/.openclaw/skills/whisper-stt/scripts/transcribe.py recording.m4a --language zh --output txt\n\nGenerate subtitles (SRT):\n\npython ~/.openclaw/skills/whisper-stt/scripts/transcribe.py video.mp4 --output srt > subtitles.srt\n\nUse faster model:\n\npython ~/.openclaw/skills/whisper-stt/scripts/transcribe.py audio.mp3 --model tiny --output txt\n\nHigh accuracy (slower):\n\npython ~/.openclaw/skills/whisper-stt/scripts/transcribe.py audio.mp3 --model large-v3 --output txt" }, { "title": "Model Selection Guide", "body": "ModelSpeedAccuracyVRAM/RAMBest Fortiny~32xBasic~1GBQuick tests, low resourcebase~16xGood~1GBBalanced speed/accuracysmall~6xBetter~2GBBetter accuracymedium~2xVery Good~5GBHigh accuracylarge1xExcellent~10GBBest qualitylarge-v3-turbo~8xExcellent~6GBFast + accurate (recommended)" }, { "title": "Troubleshooting", "body": "\"ModuleNotFoundError: No module named 'whisper'\"\n→ Run: pip install openai-whisper torch\n\n\"ffmpeg not found\"\n→ Install ffmpeg or convert audio to WAV format first\n\nSlow transcription\n→ Use smaller model (tiny/base) or ensure GPU is available (Apple Silicon MPS, NVIDIA CUDA)\n\nPoor accuracy on Chinese\n→ Use --language zh explicitly and consider larger model (medium/large)" }, { "title": "Output Formats", "body": "json: Full result with segments, timestamps, and metadata\ntxt: Plain text transcription only\nsrt: SubRip subtitle format with timing\nvtt: WebVTT subtitle format for web players" }, { "title": "Credits", "body": "Powered by OpenAI Whisper - open source speech recognition." } ], "body": "Whisper STT Skill\n\nFree, local speech-to-text using OpenAI Whisper.\n\nPrerequisites\n\nInstall dependencies (one-time setup):\n\npip install openai-whisper torch\n\n\nOptional: Install ffmpeg for broader format support:\n\nmacOS: brew install ffmpeg\nUbuntu: sudo apt install ffmpeg\nUsage\nTranscribe an audio file\npython ~/.openclaw/skills/whisper-stt/scripts/transcribe.py \n\nOptions\nOption\tDescription\n--model\tModel size: tiny, base, small, medium, large, large-v3-turbo (default: base)\n--language, -l\tLanguage code: zh, en, ja, etc. (auto-detect if not specified)\n--output, -o\tOutput format: json, txt, srt, vtt (default: json)\nExamples\n\nChinese audio to text:\n\npython ~/.openclaw/skills/whisper-stt/scripts/transcribe.py recording.m4a --language zh --output txt\n\n\nGenerate subtitles (SRT):\n\npython ~/.openclaw/skills/whisper-stt/scripts/transcribe.py video.mp4 --output srt > subtitles.srt\n\n\nUse faster model:\n\npython ~/.openclaw/skills/whisper-stt/scripts/transcribe.py audio.mp3 --model tiny --output txt\n\n\nHigh accuracy (slower):\n\npython ~/.openclaw/skills/whisper-stt/scripts/transcribe.py audio.mp3 --model large-v3 --output txt\n\nModel Selection Guide\nModel\tSpeed\tAccuracy\tVRAM/RAM\tBest For\ntiny\t~32x\tBasic\t~1GB\tQuick tests, low resource\nbase\t~16x\tGood\t~1GB\tBalanced speed/accuracy\nsmall\t~6x\tBetter\t~2GB\tBetter accuracy\nmedium\t~2x\tVery Good\t~5GB\tHigh accuracy\nlarge\t1x\tExcellent\t~10GB\tBest quality\nlarge-v3-turbo\t~8x\tExcellent\t~6GB\tFast + accurate (recommended)\nTroubleshooting\n\n\"ModuleNotFoundError: No module named 'whisper'\" → Run: pip install openai-whisper torch\n\n\"ffmpeg not found\" → Install ffmpeg or convert audio to WAV format first\n\nSlow transcription → Use smaller model (tiny/base) or ensure GPU is available (Apple Silicon MPS, NVIDIA CUDA)\n\nPoor accuracy on Chinese → Use --language zh explicitly and consider larger model (medium/large)\n\nOutput Formats\njson: Full result with segments, timestamps, and metadata\ntxt: Plain text transcription only\nsrt: SubRip subtitle format with timing\nvtt: WebVTT subtitle format for web players\nCredits\n\nPowered by OpenAI Whisper - open source speech recognition." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/nickylin/whisper-stt", "publisherUrl": "https://clawhub.ai/nickylin/whisper-stt", "owner": "nickylin", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/whisper-stt", "downloadUrl": "https://openagent3.xyz/downloads/whisper-stt", "agentUrl": "https://openagent3.xyz/skills/whisper-stt/agent", "manifestUrl": "https://openagent3.xyz/skills/whisper-stt/agent.json", "briefUrl": "https://openagent3.xyz/skills/whisper-stt/agent.md" } }