{
  "schemaVersion": "1.0",
  "item": {
    "slug": "browser-audio-capture",
    "name": "Browser Audio Capture",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/jarvis563/browser-audio-capture",
    "canonicalUrl": "https://clawhub.ai/jarvis563/browser-audio-capture",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/browser-audio-capture",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browser-audio-capture",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/browser_capture/__init__.py",
      "scripts/browser_capture/audio_capture.py",
      "scripts/browser_capture/cdp_client.py",
      "scripts/browser_capture/cli.py",
      "scripts/extension/README.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/browser-audio-capture"
    },
    "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/browser-audio-capture",
    "agentPageUrl": "https://openagent3.xyz/skills/browser-audio-capture/agent",
    "manifestUrl": "https://openagent3.xyz/skills/browser-audio-capture/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/browser-audio-capture/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": "Browser Audio Capture",
        "body": "Give any AI agent ears for the browser. One Chrome extension captures audio from any tab — meetings, YouTube, podcasts, webinars, courses, earnings calls — and streams it to your AI pipeline."
      },
      {
        "title": "Why Use This",
        "body": "Your AI agent can't hear anything happening in your browser. This skill fixes that. Capture audio from any Chrome tab and stream it to your agent — no API keys, no OAuth, no per-platform integrations.\n\nUse cases: meeting summaries, YouTube/podcast notes, competitive intel from earnings calls, auto-notes from online courses, customer call analysis — anything that plays audio in a browser tab.\n\nWorks with any AI agent — Claude, ChatGPT, OpenClaw, LangChain, CrewAI, or your own. If your agent can run shell commands or receive HTTP, it gets browser audio."
      },
      {
        "title": "Prerequisites",
        "body": "Chrome with remote debugging:\n\n# macOS\n/Applications/Google\\ Chrome.app/Contents/MacOS/Google\\ Chrome \\\n  --remote-debugging-port=9222 --user-data-dir=$HOME/.chrome-debug-profile &\n\nPython 3.9+ with aiohttp: pip install aiohttp"
      },
      {
        "title": "CLI (any agent that can exec)",
        "body": "# List tabs — meetings flagged with 🎙️\npython3 -m browser_capture.cli tabs\n\n# Auto-detect and capture meeting tab\npython3 -m browser_capture.cli capture\n\n# Continuous watch mode\npython3 -m browser_capture.cli watch --interval 15\n\n# Stop\npython3 -m browser_capture.cli stop"
      },
      {
        "title": "Chrome Extension (one-click, persistent)",
        "body": "chrome://extensions/ → Developer mode → Load unpacked → scripts/extension/\nJoin a meeting → click Percept icon → Start Capturing\nClose popup — capture continues in background"
      },
      {
        "title": "Supported Platforms",
        "body": "Google Meet • Zoom (web) • Microsoft Teams • Webex • Whereby • Around • Cal.com • Riverside • StreamYard • Ping • Daily.co • Jitsi • Discord — plus any future platform that runs in a browser."
      },
      {
        "title": "Audio Output",
        "body": "Streams to http://127.0.0.1:8900/audio/browser as JSON:\n\n{\n  \"sessionId\": \"browser_1709234567890\",\n  \"audio\": \"<base64 PCM16>\",\n  \"sampleRate\": 16000,\n  \"format\": \"pcm16\",\n  \"tabUrl\": \"https://meet.google.com/...\",\n  \"tabTitle\": \"Weekly Standup\"\n}\n\nConfigure endpoint in scripts/extension/offscreen.js (PERCEPT_URL). Point it at Whisper, Deepgram, NVIDIA Riva, or any transcription service."
      },
      {
        "title": "Troubleshooting",
        "body": "No tabs: Chrome needs --remote-debugging-port=9222\nButton won't click: Remove + re-add extension (MV3 caches aggressively)\nAudio not arriving: Check receiver on port 8900. Extension sends to /audio/browser"
      }
    ],
    "body": "Browser Audio Capture\n\nGive any AI agent ears for the browser. One Chrome extension captures audio from any tab — meetings, YouTube, podcasts, webinars, courses, earnings calls — and streams it to your AI pipeline.\n\nWhy Use This\n\nYour AI agent can't hear anything happening in your browser. This skill fixes that. Capture audio from any Chrome tab and stream it to your agent — no API keys, no OAuth, no per-platform integrations.\n\nUse cases: meeting summaries, YouTube/podcast notes, competitive intel from earnings calls, auto-notes from online courses, customer call analysis — anything that plays audio in a browser tab.\n\nWorks with any AI agent — Claude, ChatGPT, OpenClaw, LangChain, CrewAI, or your own. If your agent can run shell commands or receive HTTP, it gets browser audio.\n\nPrerequisites\n\nChrome with remote debugging:\n\n# macOS\n/Applications/Google\\ Chrome.app/Contents/MacOS/Google\\ Chrome \\\n  --remote-debugging-port=9222 --user-data-dir=$HOME/.chrome-debug-profile &\n\n\nPython 3.9+ with aiohttp: pip install aiohttp\n\nQuick Start\nCLI (any agent that can exec)\n# List tabs — meetings flagged with 🎙️\npython3 -m browser_capture.cli tabs\n\n# Auto-detect and capture meeting tab\npython3 -m browser_capture.cli capture\n\n# Continuous watch mode\npython3 -m browser_capture.cli watch --interval 15\n\n# Stop\npython3 -m browser_capture.cli stop\n\nChrome Extension (one-click, persistent)\nchrome://extensions/ → Developer mode → Load unpacked → scripts/extension/\nJoin a meeting → click Percept icon → Start Capturing\nClose popup — capture continues in background\nSupported Platforms\n\nGoogle Meet • Zoom (web) • Microsoft Teams • Webex • Whereby • Around • Cal.com • Riverside • StreamYard • Ping • Daily.co • Jitsi • Discord — plus any future platform that runs in a browser.\n\nAudio Output\n\nStreams to http://127.0.0.1:8900/audio/browser as JSON:\n\n{\n  \"sessionId\": \"browser_1709234567890\",\n  \"audio\": \"<base64 PCM16>\",\n  \"sampleRate\": 16000,\n  \"format\": \"pcm16\",\n  \"tabUrl\": \"https://meet.google.com/...\",\n  \"tabTitle\": \"Weekly Standup\"\n}\n\n\nConfigure endpoint in scripts/extension/offscreen.js (PERCEPT_URL). Point it at Whisper, Deepgram, NVIDIA Riva, or any transcription service.\n\nTroubleshooting\nNo tabs: Chrome needs --remote-debugging-port=9222\nButton won't click: Remove + re-add extension (MV3 caches aggressively)\nAudio not arriving: Check receiver on port 8900. Extension sends to /audio/browser"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jarvis563/browser-audio-capture",
    "publisherUrl": "https://clawhub.ai/jarvis563/browser-audio-capture",
    "owner": "jarvis563",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/browser-audio-capture",
    "downloadUrl": "https://openagent3.xyz/downloads/browser-audio-capture",
    "agentUrl": "https://openagent3.xyz/skills/browser-audio-capture/agent",
    "manifestUrl": "https://openagent3.xyz/skills/browser-audio-capture/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/browser-audio-capture/agent.md"
  }
}