{
  "schemaVersion": "1.0",
  "item": {
    "slug": "eachlabs-voice-audio",
    "name": "Eachlabs Voice Audio",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/eftalyurtseven/eachlabs-voice-audio",
    "canonicalUrl": "https://clawhub.ai/eftalyurtseven/eachlabs-voice-audio",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/eachlabs-voice-audio",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=eachlabs-voice-audio",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/MODELS.md"
    ],
    "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/eachlabs-voice-audio"
    },
    "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/eachlabs-voice-audio",
    "agentPageUrl": "https://openagent3.xyz/skills/eachlabs-voice-audio/agent",
    "manifestUrl": "https://openagent3.xyz/skills/eachlabs-voice-audio/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/eachlabs-voice-audio/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": "EachLabs Voice & Audio",
        "body": "Text-to-speech, speech-to-text transcription, voice conversion, and audio utilities via the EachLabs Predictions API."
      },
      {
        "title": "Authentication",
        "body": "Header: X-API-Key: <your-api-key>\n\nSet the EACHLABS_API_KEY environment variable. Get your key at eachlabs.ai."
      },
      {
        "title": "Text-to-Speech",
        "body": "ModelSlugBest ForElevenLabs TTSelevenlabs-text-to-speechHigh quality TTSElevenLabs TTS w/ Timestampselevenlabs-text-to-speech-with-timestampTTS with word timingElevenLabs Text to Dialogueelevenlabs-text-to-dialogueMulti-speaker dialogueElevenLabs Sound Effectselevenlabs-sound-effectsSound effect generationElevenLabs Voice Design v2elevenlabs-voice-design-v2Custom voice designKling V1 TTSkling-v1-ttsKling text-to-speechKokoro 82Mkokoro-82mLightweight TTSPlay AI Dialogplay-ai-text-to-speech-dialogDialog TTSStable Audio 2.5stable-audio-2-5-text-to-audioText to audio"
      },
      {
        "title": "Speech-to-Text",
        "body": "ModelSlugBest ForElevenLabs Scribe v2elevenlabs-speech-to-text-scribe-v2Best quality transcriptionElevenLabs STTelevenlabs-speech-to-textStandard transcriptionWizper with Timestampwizper-with-timestampTimestamped transcriptionWizperwizperBasic transcriptionWhisperwhisperOpen-source transcriptionWhisper Diarizationwhisper-diarizationSpeaker identificationIncredibly Fast Whisperincredibly-fast-whisperFastest transcription"
      },
      {
        "title": "Voice Conversion & Cloning",
        "body": "ModelSlugBest ForRVC v2rvc-v2Voice conversionTrain RVCtrain-rvcTrain custom voice modelElevenLabs Voice Cloneelevenlabs-voice-cloneVoice cloningElevenLabs Voice Changerelevenlabs-voice-changerVoice transformationElevenLabs Voice Design v3elevenlabs-voice-design-v3Advanced voice designElevenLabs Dubbingelevenlabs-dubbingVideo dubbingChatterbox S2Schatterbox-speech-to-speechSpeech to speechOpen VoiceopenvoiceOpen-source voice cloneXTTS v2xtts-v2Multi-language voice cloneStable Audio 2.5 Inpaintstable-audio-2-5-inpaintAudio inpaintingStable Audio 2.5 A2Astable-audio-2-5-audio-to-audioAudio transformationAudio Trimmeraudio-trimmer-with-fadeAudio trimming with fade"
      },
      {
        "title": "Audio Utilities",
        "body": "ModelSlugBest ForFFmpeg Merge Audio Videoffmpeg-api-merge-audio-videoMerge audio with videoToolkit Video ConverttoolkitVideo/audio conversion"
      },
      {
        "title": "Prediction Flow",
        "body": "Check model GET https://api.eachlabs.ai/v1/model?slug=<slug> — validates the model exists and returns the request_schema with exact input parameters. Always do this before creating a prediction to ensure correct inputs.\nPOST https://api.eachlabs.ai/v1/prediction with model slug, version \"0.0.1\", and input matching the schema\nPoll GET https://api.eachlabs.ai/v1/prediction/{id} until status is \"success\" or \"failed\"\nExtract the output from the response"
      },
      {
        "title": "Text-to-Speech with ElevenLabs",
        "body": "curl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"elevenlabs-text-to-speech\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"text\": \"Welcome to our product demo. Today we will walk through the key features.\",\n      \"voice_id\": \"EXAVITQu4vr4xnSDxMaL\",\n      \"model_id\": \"eleven_v3\",\n      \"stability\": 0.5,\n      \"similarity_boost\": 0.7\n    }\n  }'"
      },
      {
        "title": "Transcription with ElevenLabs Scribe",
        "body": "curl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"elevenlabs-speech-to-text-scribe-v2\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"media_url\": \"https://example.com/recording.mp3\",\n      \"diarize\": true,\n      \"timestamps_granularity\": \"word\"\n    }\n  }'"
      },
      {
        "title": "Transcription with Wizper (Whisper)",
        "body": "curl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"wizper-with-timestamp\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"audio_url\": \"https://example.com/audio.mp3\",\n      \"language\": \"en\",\n      \"task\": \"transcribe\",\n      \"chunk_level\": \"segment\"\n    }\n  }'"
      },
      {
        "title": "Speaker Diarization with Whisper",
        "body": "curl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"whisper-diarization\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"file_url\": \"https://example.com/meeting.mp3\",\n      \"num_speakers\": 3,\n      \"language\": \"en\",\n      \"group_segments\": true\n    }\n  }'"
      },
      {
        "title": "Voice Conversion with RVC v2",
        "body": "curl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"rvc-v2\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"input_audio\": \"https://example.com/vocals.wav\",\n      \"rvc_model\": \"CUSTOM\",\n      \"custom_rvc_model_download_url\": \"https://example.com/my-voice-model.zip\",\n      \"pitch_change\": 0,\n      \"output_format\": \"wav\"\n    }\n  }'"
      },
      {
        "title": "Merge Audio with Video",
        "body": "curl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"ffmpeg-api-merge-audio-video\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"video_url\": \"https://example.com/video.mp4\",\n      \"audio_url\": \"https://example.com/narration.mp3\",\n      \"start_offset\": 0\n    }\n  }'"
      },
      {
        "title": "ElevenLabs Voice IDs",
        "body": "The elevenlabs-text-to-speech model supports these voice IDs. Pass the raw ID string:\n\nVoice IDNotesEXAVITQu4vr4xnSDxMaLDefault voice9BWtsMINqrJLrRacOk9x—CwhRBWXzGAHq8TQ4Fs17—FGY2WhTYpPnrIDTdsKH5—JBFqnCBsd6RMkjVDRZzb—N2lVS1w4EtoT3dr4eOWO—TX3LPaxmHKxFdv7VOQHJ—XB0fDUnXU5powFXDhCwa—onwK4e9ZLuTAKqWW03F9—pFZP5JQG7iQjIQuC4Bku—"
      },
      {
        "title": "Parameter Reference",
        "body": "See references/MODELS.md for complete parameter details for each model."
      }
    ],
    "body": "EachLabs Voice & Audio\n\nText-to-speech, speech-to-text transcription, voice conversion, and audio utilities via the EachLabs Predictions API.\n\nAuthentication\nHeader: X-API-Key: <your-api-key>\n\n\nSet the EACHLABS_API_KEY environment variable. Get your key at eachlabs.ai.\n\nAvailable Models\nText-to-Speech\nModel\tSlug\tBest For\nElevenLabs TTS\televenlabs-text-to-speech\tHigh quality TTS\nElevenLabs TTS w/ Timestamps\televenlabs-text-to-speech-with-timestamp\tTTS with word timing\nElevenLabs Text to Dialogue\televenlabs-text-to-dialogue\tMulti-speaker dialogue\nElevenLabs Sound Effects\televenlabs-sound-effects\tSound effect generation\nElevenLabs Voice Design v2\televenlabs-voice-design-v2\tCustom voice design\nKling V1 TTS\tkling-v1-tts\tKling text-to-speech\nKokoro 82M\tkokoro-82m\tLightweight TTS\nPlay AI Dialog\tplay-ai-text-to-speech-dialog\tDialog TTS\nStable Audio 2.5\tstable-audio-2-5-text-to-audio\tText to audio\nSpeech-to-Text\nModel\tSlug\tBest For\nElevenLabs Scribe v2\televenlabs-speech-to-text-scribe-v2\tBest quality transcription\nElevenLabs STT\televenlabs-speech-to-text\tStandard transcription\nWizper with Timestamp\twizper-with-timestamp\tTimestamped transcription\nWizper\twizper\tBasic transcription\nWhisper\twhisper\tOpen-source transcription\nWhisper Diarization\twhisper-diarization\tSpeaker identification\nIncredibly Fast Whisper\tincredibly-fast-whisper\tFastest transcription\nVoice Conversion & Cloning\nModel\tSlug\tBest For\nRVC v2\trvc-v2\tVoice conversion\nTrain RVC\ttrain-rvc\tTrain custom voice model\nElevenLabs Voice Clone\televenlabs-voice-clone\tVoice cloning\nElevenLabs Voice Changer\televenlabs-voice-changer\tVoice transformation\nElevenLabs Voice Design v3\televenlabs-voice-design-v3\tAdvanced voice design\nElevenLabs Dubbing\televenlabs-dubbing\tVideo dubbing\nChatterbox S2S\tchatterbox-speech-to-speech\tSpeech to speech\nOpen Voice\topenvoice\tOpen-source voice clone\nXTTS v2\txtts-v2\tMulti-language voice clone\nStable Audio 2.5 Inpaint\tstable-audio-2-5-inpaint\tAudio inpainting\nStable Audio 2.5 A2A\tstable-audio-2-5-audio-to-audio\tAudio transformation\nAudio Trimmer\taudio-trimmer-with-fade\tAudio trimming with fade\nAudio Utilities\nModel\tSlug\tBest For\nFFmpeg Merge Audio Video\tffmpeg-api-merge-audio-video\tMerge audio with video\nToolkit Video Convert\ttoolkit\tVideo/audio conversion\nPrediction Flow\nCheck model GET https://api.eachlabs.ai/v1/model?slug=<slug> — validates the model exists and returns the request_schema with exact input parameters. Always do this before creating a prediction to ensure correct inputs.\nPOST https://api.eachlabs.ai/v1/prediction with model slug, version \"0.0.1\", and input matching the schema\nPoll GET https://api.eachlabs.ai/v1/prediction/{id} until status is \"success\" or \"failed\"\nExtract the output from the response\nExamples\nText-to-Speech with ElevenLabs\ncurl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"elevenlabs-text-to-speech\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"text\": \"Welcome to our product demo. Today we will walk through the key features.\",\n      \"voice_id\": \"EXAVITQu4vr4xnSDxMaL\",\n      \"model_id\": \"eleven_v3\",\n      \"stability\": 0.5,\n      \"similarity_boost\": 0.7\n    }\n  }'\n\nTranscription with ElevenLabs Scribe\ncurl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"elevenlabs-speech-to-text-scribe-v2\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"media_url\": \"https://example.com/recording.mp3\",\n      \"diarize\": true,\n      \"timestamps_granularity\": \"word\"\n    }\n  }'\n\nTranscription with Wizper (Whisper)\ncurl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"wizper-with-timestamp\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"audio_url\": \"https://example.com/audio.mp3\",\n      \"language\": \"en\",\n      \"task\": \"transcribe\",\n      \"chunk_level\": \"segment\"\n    }\n  }'\n\nSpeaker Diarization with Whisper\ncurl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"whisper-diarization\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"file_url\": \"https://example.com/meeting.mp3\",\n      \"num_speakers\": 3,\n      \"language\": \"en\",\n      \"group_segments\": true\n    }\n  }'\n\nVoice Conversion with RVC v2\ncurl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"rvc-v2\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"input_audio\": \"https://example.com/vocals.wav\",\n      \"rvc_model\": \"CUSTOM\",\n      \"custom_rvc_model_download_url\": \"https://example.com/my-voice-model.zip\",\n      \"pitch_change\": 0,\n      \"output_format\": \"wav\"\n    }\n  }'\n\nMerge Audio with Video\ncurl -X POST https://api.eachlabs.ai/v1/prediction \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $EACHLABS_API_KEY\" \\\n  -d '{\n    \"model\": \"ffmpeg-api-merge-audio-video\",\n    \"version\": \"0.0.1\",\n    \"input\": {\n      \"video_url\": \"https://example.com/video.mp4\",\n      \"audio_url\": \"https://example.com/narration.mp3\",\n      \"start_offset\": 0\n    }\n  }'\n\nElevenLabs Voice IDs\n\nThe elevenlabs-text-to-speech model supports these voice IDs. Pass the raw ID string:\n\nVoice ID\tNotes\nEXAVITQu4vr4xnSDxMaL\tDefault voice\n9BWtsMINqrJLrRacOk9x\t—\nCwhRBWXzGAHq8TQ4Fs17\t—\nFGY2WhTYpPnrIDTdsKH5\t—\nJBFqnCBsd6RMkjVDRZzb\t—\nN2lVS1w4EtoT3dr4eOWO\t—\nTX3LPaxmHKxFdv7VOQHJ\t—\nXB0fDUnXU5powFXDhCwa\t—\nonwK4e9ZLuTAKqWW03F9\t—\npFZP5JQG7iQjIQuC4Bku\t—\nParameter Reference\n\nSee references/MODELS.md for complete parameter details for each model."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/eftalyurtseven/eachlabs-voice-audio",
    "publisherUrl": "https://clawhub.ai/eftalyurtseven/eachlabs-voice-audio",
    "owner": "eftalyurtseven",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/eachlabs-voice-audio",
    "downloadUrl": "https://openagent3.xyz/downloads/eachlabs-voice-audio",
    "agentUrl": "https://openagent3.xyz/skills/eachlabs-voice-audio/agent",
    "manifestUrl": "https://openagent3.xyz/skills/eachlabs-voice-audio/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/eachlabs-voice-audio/agent.md"
  }
}