{
  "schemaVersion": "1.0",
  "item": {
    "slug": "discord-voice",
    "name": "Discord Voice",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/avatarneil/discord-voice",
    "canonicalUrl": "https://clawhub.ai/avatarneil/discord-voice",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/discord-voice",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=discord-voice",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CHANGELOG.md",
      ".oxlintrc.json",
      "openclaw.plugin.json",
      "README.md",
      "package-lock.json",
      "package.json"
    ],
    "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/discord-voice"
    },
    "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/discord-voice",
    "agentPageUrl": "https://openagent3.xyz/skills/discord-voice/agent",
    "manifestUrl": "https://openagent3.xyz/skills/discord-voice/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/discord-voice/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Discord Voice Plugin for Clawdbot",
        "body": "Real-time voice conversations in Discord voice channels. Join a voice channel, speak, and have your words transcribed, processed by Claude, and spoken back."
      },
      {
        "title": "Features",
        "body": "Join/Leave Voice Channels: Via slash commands, CLI, or agent tool\nVoice Activity Detection (VAD): Automatically detects when users are speaking\nSpeech-to-Text: Whisper API (OpenAI), Deepgram, or Local Whisper (Offline)\nStreaming STT: Real-time transcription with Deepgram WebSocket (~1s latency reduction)\nAgent Integration: Transcribed speech is routed through the Clawdbot agent\nText-to-Speech: OpenAI TTS, ElevenLabs, or Kokoro (Local/Offline)\nAudio Playback: Responses are spoken back in the voice channel\nBarge-in Support: Stops speaking immediately when user starts talking\nAuto-reconnect: Automatic heartbeat monitoring and reconnection on disconnect"
      },
      {
        "title": "Requirements",
        "body": "Discord bot with voice permissions (Connect, Speak, Use Voice Activity)\nAPI keys for STT and TTS providers\nSystem dependencies for voice:\n\nffmpeg (audio processing)\nNative build tools for @discordjs/opus and sodium-native"
      },
      {
        "title": "1. Install System Dependencies",
        "body": "# Ubuntu/Debian\nsudo apt-get install ffmpeg build-essential python3\n\n# Fedora/RHEL\nsudo dnf install ffmpeg gcc-c++ make python3\n\n# macOS\nbrew install ffmpeg"
      },
      {
        "title": "2. Install via ClawdHub",
        "body": "clawdhub install discord-voice\n\nOr manually:\n\ncd ~/.clawdbot/extensions\ngit clone <repository-url> discord-voice\ncd discord-voice\nnpm install"
      },
      {
        "title": "3. Configure in clawdbot.json",
        "body": "{\n  plugins: {\n    entries: {\n      \"discord-voice\": {\n        enabled: true,\n        config: {\n          sttProvider: \"local-whisper\",\n          ttsProvider: \"openai\",\n          ttsVoice: \"nova\",\n          vadSensitivity: \"medium\",\n          allowedUsers: [], // Empty = allow all users\n          silenceThresholdMs: 1500,\n          maxRecordingMs: 30000,\n          openai: {\n            apiKey: \"sk-...\", // Or use OPENAI_API_KEY env var\n          },\n        },\n      },\n    },\n  },\n}"
      },
      {
        "title": "4. Discord Bot Setup",
        "body": "Ensure your Discord bot has these permissions:\n\nConnect - Join voice channels\nSpeak - Play audio\nUse Voice Activity - Detect when users speak\n\nAdd these to your bot's OAuth2 URL or configure in Discord Developer Portal."
      },
      {
        "title": "Configuration",
        "body": "OptionTypeDefaultDescriptionenabledbooleantrueEnable/disable the pluginsttProviderstring\"local-whisper\"\"whisper\", \"deepgram\", or \"local-whisper\"streamingSTTbooleantrueUse streaming STT (Deepgram only, ~1s faster)ttsProviderstring\"openai\"\"openai\" or \"elevenlabs\"ttsVoicestring\"nova\"Voice ID for TTSvadSensitivitystring\"medium\"\"low\", \"medium\", or \"high\"bargeInbooleantrueStop speaking when user talksallowedUsersstring[][]User IDs allowed (empty = all)silenceThresholdMsnumber1500Silence before processing (ms)maxRecordingMsnumber30000Max recording length (ms)heartbeatIntervalMsnumber30000Connection health check intervalautoJoinChannelstringundefinedChannel ID to auto-join on startup"
      },
      {
        "title": "Provider Configuration",
        "body": "OpenAI (Whisper + TTS)\n\n{\n  openai: {\n    apiKey: \"sk-...\",\n    whisperModel: \"whisper-1\",\n    ttsModel: \"tts-1\",\n  },\n}\n\nElevenLabs (TTS only)\n\n{\n  elevenlabs: {\n    apiKey: \"...\",\n    voiceId: \"21m00Tcm4TlvDq8ikWAM\", // Rachel\n    modelId: \"eleven_multilingual_v2\",\n  },\n}\n\nDeepgram (STT only)\n\n{\n  deepgram: {\n    apiKey: \"...\",\n    model: \"nova-2\",\n  },\n}"
      },
      {
        "title": "Slash Commands (Discord)",
        "body": "Once registered with Discord, use these commands:\n\n/discord_voice join <channel> - Join a voice channel\n/discord_voice leave - Leave the current voice channel\n/discord_voice status - Show voice connection status"
      },
      {
        "title": "CLI Commands",
        "body": "# Join a voice channel\nclawdbot discord_voice join <channelId>\n\n# Leave voice\nclawdbot discord_voice leave --guild <guildId>\n\n# Check status\nclawdbot discord_voice status"
      },
      {
        "title": "Agent Tool",
        "body": "The agent can use the discord_voice tool:\n\nJoin voice channel 1234567890\n\nThe tool supports actions:\n\njoin - Join a voice channel (requires channelId)\nleave - Leave voice channel\nspeak - Speak text in the voice channel\nstatus - Get current voice status"
      },
      {
        "title": "How It Works",
        "body": "Join: Bot joins the specified voice channel\nListen: VAD detects when users start/stop speaking\nRecord: Audio is buffered while user speaks\nTranscribe: On silence, audio is sent to STT provider\nProcess: Transcribed text is sent to Clawdbot agent\nSynthesize: Agent response is converted to audio via TTS\nPlay: Audio is played back in the voice channel"
      },
      {
        "title": "Streaming STT (Deepgram)",
        "body": "When using Deepgram as your STT provider, streaming mode is enabled by default. This provides:\n\n~1 second faster end-to-end latency\nReal-time feedback with interim transcription results\nAutomatic keep-alive to prevent connection timeouts\nFallback to batch transcription if streaming fails\n\nTo use streaming STT:\n\n{\n  sttProvider: \"deepgram\",\n  streamingSTT: true, // default\n  deepgram: {\n    apiKey: \"...\",\n    model: \"nova-2\",\n  },\n}"
      },
      {
        "title": "Barge-in Support",
        "body": "When enabled (default), the bot will immediately stop speaking if a user starts talking. This creates a more natural conversational flow where you can interrupt the bot.\n\nTo disable (let the bot finish speaking):\n\n{\n  bargeIn: false,\n}"
      },
      {
        "title": "Auto-reconnect",
        "body": "The plugin includes automatic connection health monitoring:\n\nHeartbeat checks every 30 seconds (configurable)\nAuto-reconnect on disconnect with exponential backoff\nMax 3 attempts before giving up\n\nIf the connection drops, you'll see logs like:\n\n[discord-voice] Disconnected from voice channel\n[discord-voice] Reconnection attempt 1/3\n[discord-voice] Reconnected successfully"
      },
      {
        "title": "VAD Sensitivity",
        "body": "low: Picks up quiet speech, may trigger on background noise\nmedium: Balanced (recommended)\nhigh: Requires louder, clearer speech"
      },
      {
        "title": "\"Discord client not available\"",
        "body": "Ensure the Discord channel is configured and the bot is connected before using voice."
      },
      {
        "title": "Opus/Sodium build errors",
        "body": "Install build tools:\n\nnpm install -g node-gyp\nnpm rebuild @discordjs/opus sodium-native"
      },
      {
        "title": "No audio heard",
        "body": "Check bot has Connect + Speak permissions\nCheck bot isn't server muted\nVerify TTS API key is valid"
      },
      {
        "title": "Transcription not working",
        "body": "Check STT API key is valid\nCheck audio is being recorded (see debug logs)\nTry adjusting VAD sensitivity"
      },
      {
        "title": "Enable debug logging",
        "body": "DEBUG=discord-voice clawdbot gateway start"
      },
      {
        "title": "Environment Variables",
        "body": "VariableDescriptionDISCORD_TOKENDiscord bot token (required)OPENAI_API_KEYOpenAI API key (Whisper + TTS)ELEVENLABS_API_KEYElevenLabs API keyDEEPGRAM_API_KEYDeepgram API key"
      },
      {
        "title": "Limitations",
        "body": "Only one voice channel per guild at a time\nMaximum recording length: 30 seconds (configurable)\nRequires stable network for real-time audio\nTTS output may have slight delay due to synthesis"
      },
      {
        "title": "License",
        "body": "MIT"
      }
    ],
    "body": "Discord Voice Plugin for Clawdbot\n\nReal-time voice conversations in Discord voice channels. Join a voice channel, speak, and have your words transcribed, processed by Claude, and spoken back.\n\nFeatures\nJoin/Leave Voice Channels: Via slash commands, CLI, or agent tool\nVoice Activity Detection (VAD): Automatically detects when users are speaking\nSpeech-to-Text: Whisper API (OpenAI), Deepgram, or Local Whisper (Offline)\nStreaming STT: Real-time transcription with Deepgram WebSocket (~1s latency reduction)\nAgent Integration: Transcribed speech is routed through the Clawdbot agent\nText-to-Speech: OpenAI TTS, ElevenLabs, or Kokoro (Local/Offline)\nAudio Playback: Responses are spoken back in the voice channel\nBarge-in Support: Stops speaking immediately when user starts talking\nAuto-reconnect: Automatic heartbeat monitoring and reconnection on disconnect\nRequirements\nDiscord bot with voice permissions (Connect, Speak, Use Voice Activity)\nAPI keys for STT and TTS providers\nSystem dependencies for voice:\nffmpeg (audio processing)\nNative build tools for @discordjs/opus and sodium-native\nInstallation\n1. Install System Dependencies\n# Ubuntu/Debian\nsudo apt-get install ffmpeg build-essential python3\n\n# Fedora/RHEL\nsudo dnf install ffmpeg gcc-c++ make python3\n\n# macOS\nbrew install ffmpeg\n\n2. Install via ClawdHub\nclawdhub install discord-voice\n\n\nOr manually:\n\ncd ~/.clawdbot/extensions\ngit clone <repository-url> discord-voice\ncd discord-voice\nnpm install\n\n3. Configure in clawdbot.json\n{\n  plugins: {\n    entries: {\n      \"discord-voice\": {\n        enabled: true,\n        config: {\n          sttProvider: \"local-whisper\",\n          ttsProvider: \"openai\",\n          ttsVoice: \"nova\",\n          vadSensitivity: \"medium\",\n          allowedUsers: [], // Empty = allow all users\n          silenceThresholdMs: 1500,\n          maxRecordingMs: 30000,\n          openai: {\n            apiKey: \"sk-...\", // Or use OPENAI_API_KEY env var\n          },\n        },\n      },\n    },\n  },\n}\n\n4. Discord Bot Setup\n\nEnsure your Discord bot has these permissions:\n\nConnect - Join voice channels\nSpeak - Play audio\nUse Voice Activity - Detect when users speak\n\nAdd these to your bot's OAuth2 URL or configure in Discord Developer Portal.\n\nConfiguration\nOption\tType\tDefault\tDescription\nenabled\tboolean\ttrue\tEnable/disable the plugin\nsttProvider\tstring\t\"local-whisper\"\t\"whisper\", \"deepgram\", or \"local-whisper\"\nstreamingSTT\tboolean\ttrue\tUse streaming STT (Deepgram only, ~1s faster)\nttsProvider\tstring\t\"openai\"\t\"openai\" or \"elevenlabs\"\nttsVoice\tstring\t\"nova\"\tVoice ID for TTS\nvadSensitivity\tstring\t\"medium\"\t\"low\", \"medium\", or \"high\"\nbargeIn\tboolean\ttrue\tStop speaking when user talks\nallowedUsers\tstring[]\t[]\tUser IDs allowed (empty = all)\nsilenceThresholdMs\tnumber\t1500\tSilence before processing (ms)\nmaxRecordingMs\tnumber\t30000\tMax recording length (ms)\nheartbeatIntervalMs\tnumber\t30000\tConnection health check interval\nautoJoinChannel\tstring\tundefined\tChannel ID to auto-join on startup\nProvider Configuration\nOpenAI (Whisper + TTS)\n{\n  openai: {\n    apiKey: \"sk-...\",\n    whisperModel: \"whisper-1\",\n    ttsModel: \"tts-1\",\n  },\n}\n\nElevenLabs (TTS only)\n{\n  elevenlabs: {\n    apiKey: \"...\",\n    voiceId: \"21m00Tcm4TlvDq8ikWAM\", // Rachel\n    modelId: \"eleven_multilingual_v2\",\n  },\n}\n\nDeepgram (STT only)\n{\n  deepgram: {\n    apiKey: \"...\",\n    model: \"nova-2\",\n  },\n}\n\nUsage\nSlash Commands (Discord)\n\nOnce registered with Discord, use these commands:\n\n/discord_voice join <channel> - Join a voice channel\n/discord_voice leave - Leave the current voice channel\n/discord_voice status - Show voice connection status\nCLI Commands\n# Join a voice channel\nclawdbot discord_voice join <channelId>\n\n# Leave voice\nclawdbot discord_voice leave --guild <guildId>\n\n# Check status\nclawdbot discord_voice status\n\nAgent Tool\n\nThe agent can use the discord_voice tool:\n\nJoin voice channel 1234567890\n\n\nThe tool supports actions:\n\njoin - Join a voice channel (requires channelId)\nleave - Leave voice channel\nspeak - Speak text in the voice channel\nstatus - Get current voice status\nHow It Works\nJoin: Bot joins the specified voice channel\nListen: VAD detects when users start/stop speaking\nRecord: Audio is buffered while user speaks\nTranscribe: On silence, audio is sent to STT provider\nProcess: Transcribed text is sent to Clawdbot agent\nSynthesize: Agent response is converted to audio via TTS\nPlay: Audio is played back in the voice channel\nStreaming STT (Deepgram)\n\nWhen using Deepgram as your STT provider, streaming mode is enabled by default. This provides:\n\n~1 second faster end-to-end latency\nReal-time feedback with interim transcription results\nAutomatic keep-alive to prevent connection timeouts\nFallback to batch transcription if streaming fails\n\nTo use streaming STT:\n\n{\n  sttProvider: \"deepgram\",\n  streamingSTT: true, // default\n  deepgram: {\n    apiKey: \"...\",\n    model: \"nova-2\",\n  },\n}\n\nBarge-in Support\n\nWhen enabled (default), the bot will immediately stop speaking if a user starts talking. This creates a more natural conversational flow where you can interrupt the bot.\n\nTo disable (let the bot finish speaking):\n\n{\n  bargeIn: false,\n}\n\nAuto-reconnect\n\nThe plugin includes automatic connection health monitoring:\n\nHeartbeat checks every 30 seconds (configurable)\nAuto-reconnect on disconnect with exponential backoff\nMax 3 attempts before giving up\n\nIf the connection drops, you'll see logs like:\n\n[discord-voice] Disconnected from voice channel\n[discord-voice] Reconnection attempt 1/3\n[discord-voice] Reconnected successfully\n\nVAD Sensitivity\nlow: Picks up quiet speech, may trigger on background noise\nmedium: Balanced (recommended)\nhigh: Requires louder, clearer speech\nTroubleshooting\n\"Discord client not available\"\n\nEnsure the Discord channel is configured and the bot is connected before using voice.\n\nOpus/Sodium build errors\n\nInstall build tools:\n\nnpm install -g node-gyp\nnpm rebuild @discordjs/opus sodium-native\n\nNo audio heard\nCheck bot has Connect + Speak permissions\nCheck bot isn't server muted\nVerify TTS API key is valid\nTranscription not working\nCheck STT API key is valid\nCheck audio is being recorded (see debug logs)\nTry adjusting VAD sensitivity\nEnable debug logging\nDEBUG=discord-voice clawdbot gateway start\n\nEnvironment Variables\nVariable\tDescription\nDISCORD_TOKEN\tDiscord bot token (required)\nOPENAI_API_KEY\tOpenAI API key (Whisper + TTS)\nELEVENLABS_API_KEY\tElevenLabs API key\nDEEPGRAM_API_KEY\tDeepgram API key\nLimitations\nOnly one voice channel per guild at a time\nMaximum recording length: 30 seconds (configurable)\nRequires stable network for real-time audio\nTTS output may have slight delay due to synthesis\nLicense\n\nMIT"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/avatarneil/discord-voice",
    "publisherUrl": "https://clawhub.ai/avatarneil/discord-voice",
    "owner": "avatarneil",
    "version": "0.1.6",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/discord-voice",
    "downloadUrl": "https://openagent3.xyz/downloads/discord-voice",
    "agentUrl": "https://openagent3.xyz/skills/discord-voice/agent",
    "manifestUrl": "https://openagent3.xyz/skills/discord-voice/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/discord-voice/agent.md"
  }
}