{
  "schemaVersion": "1.0",
  "item": {
    "slug": "whatsapp-voice-chat-integration-open-source",
    "name": "whatsappVoiceOpenSkill",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/syedateebulislam/whatsapp-voice-chat-integration-open-source",
    "canonicalUrl": "https://clawhub.ai/syedateebulislam/whatsapp-voice-chat-integration-open-source",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/whatsapp-voice-chat-integration-open-source",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=whatsapp-voice-chat-integration-open-source",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "COMMUNITY-NOTES.md",
      "example-custom-intents.js",
      "package.json",
      "requirements.txt",
      "SKILL.md",
      "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": "2026-04-30T16:55:25.780Z",
      "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/whatsapp-voice-chat-integration-open-source"
    },
    "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/whatsapp-voice-chat-integration-open-source",
    "agentPageUrl": "https://openagent3.xyz/skills/whatsapp-voice-chat-integration-open-source/agent",
    "manifestUrl": "https://openagent3.xyz/skills/whatsapp-voice-chat-integration-open-source/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/whatsapp-voice-chat-integration-open-source/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": "WhatsApp Voice Talk",
        "body": "Turn WhatsApp voice messages into real-time conversations. This skill provides a complete pipeline: voice → transcription → intent detection → response generation → text-to-speech.\n\nPerfect for:\n\nVoice assistants on WhatsApp\nHands-free command interfaces\nMulti-lingual chatbots\nIoT voice control (drones, smart home, etc.)"
      },
      {
        "title": "1. Install Dependencies",
        "body": "pip install openai-whisper soundfile numpy"
      },
      {
        "title": "2. Process a Voice Message",
        "body": "const { processVoiceNote } = require('./scripts/voice-processor');\nconst fs = require('fs');\n\n// Read a voice message (OGG, WAV, MP3, etc.)\nconst buffer = fs.readFileSync('voice-message.ogg');\n\n// Process it\nconst result = await processVoiceNote(buffer);\n\nconsole.log(result);\n// {\n//   status: 'success',\n//   response: \"Current weather in Delhi is 19°C, haze. Humidity is 56%.\",\n//   transcript: \"What's the weather today?\",\n//   intent: 'weather',\n//   language: 'en',\n//   timestamp: 1769860205186\n// }"
      },
      {
        "title": "3. Run Auto-Listener",
        "body": "For automatic processing of incoming WhatsApp voice messages:\n\nnode scripts/voice-listener-daemon.js\n\nThis watches ~/.clawdbot/media/inbound/ every 5 seconds and processes new voice files."
      },
      {
        "title": "How It Works",
        "body": "Incoming Voice Message\n        ↓\n    Transcribe (Whisper API)\n        ↓\n  \"What's the weather?\"\n        ↓\n  Detect Language & Intent\n        ↓\n   Match against INTENTS\n        ↓\n   Execute Handler\n        ↓\n   Generate Response\n        ↓\n   Convert to TTS\n        ↓\n  Send back via WhatsApp"
      },
      {
        "title": "Key Features",
        "body": "✅ Zero Setup Complexity - No FFmpeg, no complex dependencies. Uses soundfile + Whisper.\n\n✅ Multi-Language - Automatic English/Hindi detection. Extend easily.\n\n✅ Intent-Driven - Define custom intents with keywords and handlers.\n\n✅ Real-Time Processing - 5-10 seconds per message (after first model load).\n\n✅ Customizable - Add weather, status, commands, or anything else.\n\n✅ Production Ready - Built from real usage in Clawdbot."
      },
      {
        "title": "Weather Bot",
        "body": "// User says: \"What's the weather in Bangalore?\"\n// Response: \"Current weather in Delhi is 19°C...\"\n\n// (Built-in intent, just enable it)"
      },
      {
        "title": "Smart Home Control",
        "body": "// User says: \"Turn on the lights\"\n// Handler: Sends signal to smart home API\n// Response: \"Lights turned on\""
      },
      {
        "title": "Task Manager",
        "body": "// User says: \"Add milk to shopping list\"\n// Handler: Adds to database\n// Response: \"Added milk to your list\""
      },
      {
        "title": "Status Checker",
        "body": "// User says: \"Is the system running?\"\n// Handler: Checks system status\n// Response: \"All systems online\""
      },
      {
        "title": "Add a Custom Intent",
        "body": "Edit voice-processor.js:\n\nAdd to INTENTS map:\n\nconst INTENTS = {\n  'shopping': {\n    keywords: ['shopping', 'list', 'buy', 'खरीद'],\n    handler: 'handleShopping'\n  }\n};\n\nAdd handler:\n\nconst handlers = {\n  async handleShopping(language = 'en') {\n    return {\n      status: 'success',\n      response: language === 'en' \n        ? \"What would you like to add to your shopping list?\"\n        : \"आप अपनी शॉपिंग लिस्ट में क्या जोड़ना चाहते हैं?\"\n    };\n  }\n};"
      },
      {
        "title": "Support More Languages",
        "body": "Update detectLanguage() for your language's Unicode:\n\nconst urduChars = /[\\u0600-\\u06FF]/g; // Add this\n\nAdd language code to returns:\n\nreturn language === 'ur' ? 'Urdu response' : 'English response';\n\nSet language in transcribe.py:\n\nresult = model.transcribe(data, language=\"ur\")"
      },
      {
        "title": "Change Transcription Model",
        "body": "In transcribe.py:\n\nmodel = whisper.load_model(\"tiny\")    # Fastest, 39MB\nmodel = whisper.load_model(\"base\")    # Default, 140MB  \nmodel = whisper.load_model(\"small\")   # Better, 466MB\nmodel = whisper.load_model(\"medium\")  # Good, 1.5GB"
      },
      {
        "title": "Architecture",
        "body": "Scripts:\n\ntranscribe.py - Whisper transcription (Python)\nvoice-processor.js - Core logic (intent parsing, handlers)\nvoice-listener-daemon.js - Auto-listener watching for new messages\n\nReferences:\n\nSETUP.md - Installation and configuration\nAPI.md - Detailed function documentation"
      },
      {
        "title": "Integration with Clawdbot",
        "body": "If running as a Clawdbot skill, hook into message events:\n\n// In your Clawdbot handler\nconst { processVoiceNote } = require('skills/whatsapp-voice-talk/scripts/voice-processor');\n\nmessage.on('voice', async (audioBuffer) => {\n  const result = await processVoiceNote(audioBuffer, message.from);\n  \n  // Send response back\n  await message.reply(result.response);\n  \n  // Or send as voice (requires TTS)\n  await sendVoiceMessage(result.response);\n});"
      },
      {
        "title": "Performance",
        "body": "First run: ~30 seconds (downloads Whisper model, ~140MB)\nTypical: 5-10 seconds per message\nMemory: ~1.5GB (base model)\nLanguages: English, Hindi (easily extended)"
      },
      {
        "title": "Supported Audio Formats",
        "body": "OGG (Opus), WAV, FLAC, MP3, CAF, AIFF, and more via libsndfile.\n\nWhatsApp uses Opus-coded OGG by default — works out of the box."
      },
      {
        "title": "Troubleshooting",
        "body": "\"No module named 'whisper'\"\n\npip install openai-whisper\n\n\"No module named 'soundfile'\"\n\npip install soundfile\n\nVoice messages not processing?\n\nCheck: clawdbot status (is it running?)\nCheck: ~/.clawdbot/media/inbound/ (files arriving?)\nRun daemon manually: node scripts/voice-listener-daemon.js (see logs)\n\nSlow transcription?\nUse smaller model: whisper.load_model(\"base\") or \"tiny\""
      },
      {
        "title": "Further Reading",
        "body": "Setup Guide: See references/SETUP.md for detailed installation and configuration\nAPI Reference: See references/API.md for function signatures and examples\nExamples: Check scripts/ for working code"
      },
      {
        "title": "License",
        "body": "MIT - Use freely, customize, contribute back!\n\nBuilt for real-world use in Clawdbot. Battle-tested with multiple languages and use cases."
      }
    ],
    "body": "WhatsApp Voice Talk\n\nTurn WhatsApp voice messages into real-time conversations. This skill provides a complete pipeline: voice → transcription → intent detection → response generation → text-to-speech.\n\nPerfect for:\n\nVoice assistants on WhatsApp\nHands-free command interfaces\nMulti-lingual chatbots\nIoT voice control (drones, smart home, etc.)\nQuick Start\n1. Install Dependencies\npip install openai-whisper soundfile numpy\n\n2. Process a Voice Message\nconst { processVoiceNote } = require('./scripts/voice-processor');\nconst fs = require('fs');\n\n// Read a voice message (OGG, WAV, MP3, etc.)\nconst buffer = fs.readFileSync('voice-message.ogg');\n\n// Process it\nconst result = await processVoiceNote(buffer);\n\nconsole.log(result);\n// {\n//   status: 'success',\n//   response: \"Current weather in Delhi is 19°C, haze. Humidity is 56%.\",\n//   transcript: \"What's the weather today?\",\n//   intent: 'weather',\n//   language: 'en',\n//   timestamp: 1769860205186\n// }\n\n3. Run Auto-Listener\n\nFor automatic processing of incoming WhatsApp voice messages:\n\nnode scripts/voice-listener-daemon.js\n\n\nThis watches ~/.clawdbot/media/inbound/ every 5 seconds and processes new voice files.\n\nHow It Works\nIncoming Voice Message\n        ↓\n    Transcribe (Whisper API)\n        ↓\n  \"What's the weather?\"\n        ↓\n  Detect Language & Intent\n        ↓\n   Match against INTENTS\n        ↓\n   Execute Handler\n        ↓\n   Generate Response\n        ↓\n   Convert to TTS\n        ↓\n  Send back via WhatsApp\n\nKey Features\n\n✅ Zero Setup Complexity - No FFmpeg, no complex dependencies. Uses soundfile + Whisper.\n\n✅ Multi-Language - Automatic English/Hindi detection. Extend easily.\n\n✅ Intent-Driven - Define custom intents with keywords and handlers.\n\n✅ Real-Time Processing - 5-10 seconds per message (after first model load).\n\n✅ Customizable - Add weather, status, commands, or anything else.\n\n✅ Production Ready - Built from real usage in Clawdbot.\n\nCommon Use Cases\nWeather Bot\n// User says: \"What's the weather in Bangalore?\"\n// Response: \"Current weather in Delhi is 19°C...\"\n\n// (Built-in intent, just enable it)\n\nSmart Home Control\n// User says: \"Turn on the lights\"\n// Handler: Sends signal to smart home API\n// Response: \"Lights turned on\"\n\nTask Manager\n// User says: \"Add milk to shopping list\"\n// Handler: Adds to database\n// Response: \"Added milk to your list\"\n\nStatus Checker\n// User says: \"Is the system running?\"\n// Handler: Checks system status\n// Response: \"All systems online\"\n\nCustomization\nAdd a Custom Intent\n\nEdit voice-processor.js:\n\nAdd to INTENTS map:\nconst INTENTS = {\n  'shopping': {\n    keywords: ['shopping', 'list', 'buy', 'खरीद'],\n    handler: 'handleShopping'\n  }\n};\n\nAdd handler:\nconst handlers = {\n  async handleShopping(language = 'en') {\n    return {\n      status: 'success',\n      response: language === 'en' \n        ? \"What would you like to add to your shopping list?\"\n        : \"आप अपनी शॉपिंग लिस्ट में क्या जोड़ना चाहते हैं?\"\n    };\n  }\n};\n\nSupport More Languages\nUpdate detectLanguage() for your language's Unicode:\nconst urduChars = /[\\u0600-\\u06FF]/g; // Add this\n\nAdd language code to returns:\nreturn language === 'ur' ? 'Urdu response' : 'English response';\n\nSet language in transcribe.py:\nresult = model.transcribe(data, language=\"ur\")\n\nChange Transcription Model\n\nIn transcribe.py:\n\nmodel = whisper.load_model(\"tiny\")    # Fastest, 39MB\nmodel = whisper.load_model(\"base\")    # Default, 140MB  \nmodel = whisper.load_model(\"small\")   # Better, 466MB\nmodel = whisper.load_model(\"medium\")  # Good, 1.5GB\n\nArchitecture\n\nScripts:\n\ntranscribe.py - Whisper transcription (Python)\nvoice-processor.js - Core logic (intent parsing, handlers)\nvoice-listener-daemon.js - Auto-listener watching for new messages\n\nReferences:\n\nSETUP.md - Installation and configuration\nAPI.md - Detailed function documentation\nIntegration with Clawdbot\n\nIf running as a Clawdbot skill, hook into message events:\n\n// In your Clawdbot handler\nconst { processVoiceNote } = require('skills/whatsapp-voice-talk/scripts/voice-processor');\n\nmessage.on('voice', async (audioBuffer) => {\n  const result = await processVoiceNote(audioBuffer, message.from);\n  \n  // Send response back\n  await message.reply(result.response);\n  \n  // Or send as voice (requires TTS)\n  await sendVoiceMessage(result.response);\n});\n\nPerformance\nFirst run: ~30 seconds (downloads Whisper model, ~140MB)\nTypical: 5-10 seconds per message\nMemory: ~1.5GB (base model)\nLanguages: English, Hindi (easily extended)\nSupported Audio Formats\n\nOGG (Opus), WAV, FLAC, MP3, CAF, AIFF, and more via libsndfile.\n\nWhatsApp uses Opus-coded OGG by default — works out of the box.\n\nTroubleshooting\n\n\"No module named 'whisper'\"\n\npip install openai-whisper\n\n\n\"No module named 'soundfile'\"\n\npip install soundfile\n\n\nVoice messages not processing?\n\nCheck: clawdbot status (is it running?)\nCheck: ~/.clawdbot/media/inbound/ (files arriving?)\nRun daemon manually: node scripts/voice-listener-daemon.js (see logs)\n\nSlow transcription? Use smaller model: whisper.load_model(\"base\") or \"tiny\"\n\nFurther Reading\nSetup Guide: See references/SETUP.md for detailed installation and configuration\nAPI Reference: See references/API.md for function signatures and examples\nExamples: Check scripts/ for working code\nLicense\n\nMIT - Use freely, customize, contribute back!\n\nBuilt for real-world use in Clawdbot. Battle-tested with multiple languages and use cases."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/syedateebulislam/whatsapp-voice-chat-integration-open-source",
    "publisherUrl": "https://clawhub.ai/syedateebulislam/whatsapp-voice-chat-integration-open-source",
    "owner": "syedateebulislam",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/whatsapp-voice-chat-integration-open-source",
    "downloadUrl": "https://openagent3.xyz/downloads/whatsapp-voice-chat-integration-open-source",
    "agentUrl": "https://openagent3.xyz/skills/whatsapp-voice-chat-integration-open-source/agent",
    "manifestUrl": "https://openagent3.xyz/skills/whatsapp-voice-chat-integration-open-source/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/whatsapp-voice-chat-integration-open-source/agent.md"
  }
}