{
  "schemaVersion": "1.0",
  "item": {
    "slug": "elevenlabs-transcribe",
    "name": "Elevenlabs Transcribe",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/PaulAsjes/elevenlabs-transcribe",
    "canonicalUrl": "https://clawhub.ai/PaulAsjes/elevenlabs-transcribe",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/elevenlabs-transcribe",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=elevenlabs-transcribe",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/requirements.txt",
      "scripts/transcribe.py",
      "scripts/transcribe.sh"
    ],
    "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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-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/elevenlabs-transcribe"
    },
    "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/elevenlabs-transcribe",
    "agentPageUrl": "https://openagent3.xyz/skills/elevenlabs-transcribe/agent",
    "manifestUrl": "https://openagent3.xyz/skills/elevenlabs-transcribe/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/elevenlabs-transcribe/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": "ElevenLabs Speech-to-Text",
        "body": "Official ElevenLabs skill for speech-to-text transcription.\n\nConvert audio to text with state-of-the-art accuracy. Supports 90+ languages, speaker diarization, and realtime streaming."
      },
      {
        "title": "Prerequisites",
        "body": "ffmpeg installed (brew install ffmpeg on macOS)\nELEVENLABS_API_KEY environment variable set\nPython 3.8+ (dependencies auto-install on first run)"
      },
      {
        "title": "Usage",
        "body": "{baseDir}/scripts/transcribe.sh <audio_file> [options]\n{baseDir}/scripts/transcribe.sh --url <stream_url> [options]\n{baseDir}/scripts/transcribe.sh --mic [options]"
      },
      {
        "title": "Batch Transcription",
        "body": "Transcribe a local audio file:\n\n{baseDir}/scripts/transcribe.sh recording.mp3\n\nWith speaker identification:\n\n{baseDir}/scripts/transcribe.sh meeting.mp3 --diarize\n\nGet full JSON response with timestamps:\n\n{baseDir}/scripts/transcribe.sh interview.wav --diarize --json"
      },
      {
        "title": "Realtime Streaming",
        "body": "Stream from a URL (e.g., live radio, podcast):\n\n{baseDir}/scripts/transcribe.sh --url https://npr-ice.streamguys1.com/live.mp3\n\nTranscribe from microphone:\n\n{baseDir}/scripts/transcribe.sh --mic\n\nStream a local file in realtime (useful for testing):\n\n{baseDir}/scripts/transcribe.sh audio.mp3 --realtime"
      },
      {
        "title": "Quiet Mode for Agents",
        "body": "Suppress status messages on stderr:\n\n{baseDir}/scripts/transcribe.sh --mic --quiet"
      },
      {
        "title": "Options",
        "body": "OptionDescription--diarizeIdentify different speakers in the audio--lang CODEISO language hint (e.g., en, pt, es, fr)--jsonOutput full JSON with timestamps and metadata--eventsTag audio events (laughter, music, applause)--realtimeStream local file instead of batch processing--partialsShow interim transcripts during realtime mode-q, --quietSuppress status messages (recommended for agents)"
      },
      {
        "title": "Text Mode (default)",
        "body": "Plain text transcription:\n\nThe quick brown fox jumps over the lazy dog."
      },
      {
        "title": "JSON Mode (--json)",
        "body": "{\n  \"text\": \"The quick brown fox jumps over the lazy dog.\",\n  \"language_code\": \"eng\",\n  \"language_probability\": 0.98,\n  \"words\": [\n    {\"text\": \"The\", \"start\": 0.0, \"end\": 0.15, \"type\": \"word\", \"speaker_id\": \"speaker_0\"}\n  ]\n}"
      },
      {
        "title": "Realtime Mode",
        "body": "Final transcripts print as they're committed. With --partials:\n\n[partial] The quick\n[partial] The quick brown fox\nThe quick brown fox jumps over the lazy dog."
      },
      {
        "title": "Supported Formats",
        "body": "Audio: MP3, WAV, M4A, FLAC, OGG, WebM, AAC, AIFF, Opus\nVideo: MP4, AVI, MKV, MOV, WMV, FLV, WebM, MPEG, 3GPP\n\nLimits: Up to 3GB file size, 10 hours duration"
      },
      {
        "title": "Error Handling",
        "body": "The script exits with non-zero status on errors:\n\nMissing API key: Set ELEVENLABS_API_KEY environment variable\nFile not found: Check the file path exists\nMissing ffmpeg: Install with your package manager\nAPI errors: Check API key validity and rate limits"
      },
      {
        "title": "When to Use Each Mode",
        "body": "ScenarioCommandTranscribe a recording./transcribe.sh file.mp3Meeting with multiple speakers./transcribe.sh meeting.mp3 --diarizeLive radio/podcast stream./transcribe.sh --url <url>Voice input from user./transcribe.sh --mic --quietNeed word timestamps./transcribe.sh file.mp3 --json"
      }
    ],
    "body": "ElevenLabs Speech-to-Text\n\nOfficial ElevenLabs skill for speech-to-text transcription.\n\nConvert audio to text with state-of-the-art accuracy. Supports 90+ languages, speaker diarization, and realtime streaming.\n\nPrerequisites\nffmpeg installed (brew install ffmpeg on macOS)\nELEVENLABS_API_KEY environment variable set\nPython 3.8+ (dependencies auto-install on first run)\nUsage\n{baseDir}/scripts/transcribe.sh <audio_file> [options]\n{baseDir}/scripts/transcribe.sh --url <stream_url> [options]\n{baseDir}/scripts/transcribe.sh --mic [options]\n\nExamples\nBatch Transcription\n\nTranscribe a local audio file:\n\n{baseDir}/scripts/transcribe.sh recording.mp3\n\n\nWith speaker identification:\n\n{baseDir}/scripts/transcribe.sh meeting.mp3 --diarize\n\n\nGet full JSON response with timestamps:\n\n{baseDir}/scripts/transcribe.sh interview.wav --diarize --json\n\nRealtime Streaming\n\nStream from a URL (e.g., live radio, podcast):\n\n{baseDir}/scripts/transcribe.sh --url https://npr-ice.streamguys1.com/live.mp3\n\n\nTranscribe from microphone:\n\n{baseDir}/scripts/transcribe.sh --mic\n\n\nStream a local file in realtime (useful for testing):\n\n{baseDir}/scripts/transcribe.sh audio.mp3 --realtime\n\nQuiet Mode for Agents\n\nSuppress status messages on stderr:\n\n{baseDir}/scripts/transcribe.sh --mic --quiet\n\nOptions\nOption\tDescription\n--diarize\tIdentify different speakers in the audio\n--lang CODE\tISO language hint (e.g., en, pt, es, fr)\n--json\tOutput full JSON with timestamps and metadata\n--events\tTag audio events (laughter, music, applause)\n--realtime\tStream local file instead of batch processing\n--partials\tShow interim transcripts during realtime mode\n-q, --quiet\tSuppress status messages (recommended for agents)\nOutput Format\nText Mode (default)\n\nPlain text transcription:\n\nThe quick brown fox jumps over the lazy dog.\n\nJSON Mode (--json)\n{\n  \"text\": \"The quick brown fox jumps over the lazy dog.\",\n  \"language_code\": \"eng\",\n  \"language_probability\": 0.98,\n  \"words\": [\n    {\"text\": \"The\", \"start\": 0.0, \"end\": 0.15, \"type\": \"word\", \"speaker_id\": \"speaker_0\"}\n  ]\n}\n\nRealtime Mode\n\nFinal transcripts print as they're committed. With --partials:\n\n[partial] The quick\n[partial] The quick brown fox\nThe quick brown fox jumps over the lazy dog.\n\nSupported Formats\n\nAudio: MP3, WAV, M4A, FLAC, OGG, WebM, AAC, AIFF, Opus Video: MP4, AVI, MKV, MOV, WMV, FLV, WebM, MPEG, 3GPP\n\nLimits: Up to 3GB file size, 10 hours duration\n\nError Handling\n\nThe script exits with non-zero status on errors:\n\nMissing API key: Set ELEVENLABS_API_KEY environment variable\nFile not found: Check the file path exists\nMissing ffmpeg: Install with your package manager\nAPI errors: Check API key validity and rate limits\nWhen to Use Each Mode\nScenario\tCommand\nTranscribe a recording\t./transcribe.sh file.mp3\nMeeting with multiple speakers\t./transcribe.sh meeting.mp3 --diarize\nLive radio/podcast stream\t./transcribe.sh --url <url>\nVoice input from user\t./transcribe.sh --mic --quiet\nNeed word timestamps\t./transcribe.sh file.mp3 --json"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/PaulAsjes/elevenlabs-transcribe",
    "publisherUrl": "https://clawhub.ai/PaulAsjes/elevenlabs-transcribe",
    "owner": "PaulAsjes",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/elevenlabs-transcribe",
    "downloadUrl": "https://openagent3.xyz/downloads/elevenlabs-transcribe",
    "agentUrl": "https://openagent3.xyz/skills/elevenlabs-transcribe/agent",
    "manifestUrl": "https://openagent3.xyz/skills/elevenlabs-transcribe/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/elevenlabs-transcribe/agent.md"
  }
}