{
  "schemaVersion": "1.0",
  "item": {
    "slug": "voice-agent",
    "name": "Voice Agent",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ricardotrevisan/voice-agent",
    "canonicalUrl": "https://clawhub.ai/ricardotrevisan/voice-agent",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/voice-agent",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=voice-agent",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CHANGELOG.md",
      "SKILL.md",
      "scripts/client.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/voice-agent"
    },
    "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/voice-agent",
    "agentPageUrl": "https://openagent3.xyz/skills/voice-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/voice-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/voice-agent/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": "Voice Agent",
        "body": "This skill allows you to speak and listen to the user using a local Voice Agent API.\nIt is client-only and does not start containers or services.\nIt uses local Whisper for Speech-to-Text transcription and AWS Polly for Text-to-Speech generation."
      },
      {
        "title": "Prerequisite",
        "body": "Requires a running backend API at http://localhost:8000.\nBackend setup instructions are in this repository:\n\nREADME.md\nwalkthrough.md\nDOCKER_README.md"
      },
      {
        "title": "Behavior Guidelines",
        "body": "Audio First: When the user communicates via audio (files), your PRIMARY mode of response is Audio File.\nSilent Delivery: When sending an audio response, DO NOT send a text explanation like \"I sent an audio\". Just send the audio file.\nWorkflow:\n\nUser sends audio.\nUse transcribe to read it.\nYou think of a response.\nUse synthesize to generate the audio file.\nYou send the file.\nSTOP. Do not add text commentary.\n\n\nFailure Handling: If health fails or connection errors occur, do not attempt service management from this skill. Ask the user to start or fix the backend using the repository docs."
      },
      {
        "title": "Transcribe File",
        "body": "To transcribe an audio file with local Whisper STT, run the client script with the transcribe command.\n\npython3 {baseDir}/scripts/client.py transcribe \"/path/to/audio/file.ogg\""
      },
      {
        "title": "Synthesize to File",
        "body": "To generate audio from text with AWS Polly TTS and save it to a file, run the client script with the synthesize command.\n\npython3 {baseDir}/scripts/client.py synthesize \"Text to speak\" --output \"/path/to/output.mp3\""
      },
      {
        "title": "Health Check",
        "body": "To check if the voice agent API is running and healthy:\n\npython3 {baseDir}/scripts/client.py health"
      }
    ],
    "body": "Voice Agent\n\nThis skill allows you to speak and listen to the user using a local Voice Agent API. It is client-only and does not start containers or services. It uses local Whisper for Speech-to-Text transcription and AWS Polly for Text-to-Speech generation.\n\nPrerequisite\n\nRequires a running backend API at http://localhost:8000. Backend setup instructions are in this repository:\n\nREADME.md\nwalkthrough.md\nDOCKER_README.md\nBehavior Guidelines\nAudio First: When the user communicates via audio (files), your PRIMARY mode of response is Audio File.\nSilent Delivery: When sending an audio response, DO NOT send a text explanation like \"I sent an audio\". Just send the audio file.\nWorkflow:\nUser sends audio.\nUse transcribe to read it.\nYou think of a response.\nUse synthesize to generate the audio file.\nYou send the file.\nSTOP. Do not add text commentary.\nFailure Handling: If health fails or connection errors occur, do not attempt service management from this skill. Ask the user to start or fix the backend using the repository docs.\nTools\nTranscribe File\n\nTo transcribe an audio file with local Whisper STT, run the client script with the transcribe command.\n\npython3 {baseDir}/scripts/client.py transcribe \"/path/to/audio/file.ogg\"\n\nSynthesize to File\n\nTo generate audio from text with AWS Polly TTS and save it to a file, run the client script with the synthesize command.\n\npython3 {baseDir}/scripts/client.py synthesize \"Text to speak\" --output \"/path/to/output.mp3\"\n\nHealth Check\n\nTo check if the voice agent API is running and healthy:\n\npython3 {baseDir}/scripts/client.py health"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ricardotrevisan/voice-agent",
    "publisherUrl": "https://clawhub.ai/ricardotrevisan/voice-agent",
    "owner": "ricardotrevisan",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/voice-agent",
    "downloadUrl": "https://openagent3.xyz/downloads/voice-agent",
    "agentUrl": "https://openagent3.xyz/skills/voice-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/voice-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/voice-agent/agent.md"
  }
}