clawdbot.plugin.json

{
  "id": "discord-voice",
  "name": "Discord Voice",
  "description": "Real-time voice conversations in Discord voice channels",
  "requirements": {
    "config": {
      "discord.token": {
        "required": true,
        "description": "Discord bot token (via channels.discord.token or discord.token in main config)"
      }
    },
    "env": {
      "OPENAI_API_KEY": {
        "required": false,
        "description": "OpenAI API key — needed for whisper STT and openai TTS providers (fallback if not set in plugin config)"
      },
      "ELEVENLABS_API_KEY": {
        "required": false,
        "description": "ElevenLabs API key — needed for elevenlabs TTS provider (fallback if not set in plugin config)"
      },
      "DEEPGRAM_API_KEY": {
        "required": false,
        "description": "Deepgram API key — needed for deepgram STT provider (fallback if not set in plugin config)"
      }
    },
    "systemDependencies": ["ffmpeg"]
  },
  "configSchema": {
    "type": "object",
    "additionalProperties": true,
    "properties": {
      "enabled": { "type": "boolean", "default": true },
      "sttProvider": {
        "type": "string",
        "enum": [
          "whisper",
          "gpt4o-mini",
          "gpt4o-transcribe",
          "gpt4o-transcribe-diarize",
          "deepgram",
          "local-whisper",
          "wyoming-whisper"
        ],
        "default": "whisper"
      },
      "sttFallbackProviders": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "whisper",
            "gpt4o-mini",
            "gpt4o-transcribe",
            "gpt4o-transcribe-diarize",
            "deepgram",
            "local-whisper",
            "wyoming-whisper"
          ]
        },
        "description": "Fallback STT when primary fails (quota, rate limit, Wyoming unreachable)"
      },
      "streamingSTT": {
        "type": "boolean",
        "default": true,
        "description": "Use streaming STT for lower latency (Deepgram only)"
      },
      "ttsProvider": {
        "type": "string",
        "enum": ["openai", "elevenlabs", "deepgram", "polly", "edge", "kokoro"],
        "default": "openai",
        "description": "openai, elevenlabs, edge (free), or kokoro (free local)"
      },
      "ttsVoice": { "type": "string", "default": "nova" },
      "vadSensitivity": {
        "type": "string",
        "enum": ["low", "medium", "high"],
        "default": "medium"
      },
      "bargeIn": {
        "type": "boolean",
        "default": true,
        "description": "Stop speaking when user starts talking"
      },
      "model": {
        "type": "string",
        "description": "LLM model for voice responses (e.g., anthropic/claude-3-5-haiku-latest)"
      },
      "thinkLevel": {
        "type": "string",
        "enum": ["off", "low", "medium", "high"],
        "default": "off",
        "description": "Thinking level for voice responses (lower = faster)"
      },
      "allowedUsers": { "type": "array", "items": { "type": "string" }, "default": [] },
      "silenceThresholdMs": { "type": "number", "default": 1500 },
      "minAudioMs": { "type": "number", "default": 500 },
      "maxRecordingMs": { "type": "number", "default": 30000 },
      "heartbeatIntervalMs": {
        "type": "number",
        "default": 30000,
        "description": "Connection health check interval in ms"
      },
      "autoJoinChannel": { "type": "string", "description": "Voice channel ID to auto-join on startup" },
      "openclawRoot": { "type": "string", "description": "OpenClaw package root if auto-detection fails" },
      "thinkingSound": {
        "type": "object",
        "properties": {
          "enabled": { "type": "boolean", "default": true },
          "path": { "type": "string", "default": "assets/thinking.mp3" },
          "volume": { "type": "number", "default": 0.7, "minimum": 0, "maximum": 1 },
          "stopDelayMs": { "type": "number", "default": 50 }
        }
      },
      "openai": {
        "type": "object",
        "properties": {
          "apiKey": { "type": "string" },
          "whisperModel": { "type": "string", "default": "whisper-1" },
          "ttsModel": { "type": "string", "default": "tts-1" },
          "voice": {
            "type": "string",
            "default": "nova",
            "description": "nova, shimmer, echo, onyx, fable, alloy, ash, sage, coral"
          }
        }
      },
      "polly": {
        "type": "object",
        "properties": {
          "region": { "type": "string", "default": "us-east-1" },
          "voiceId": { "type": "string", "default": "Joanna" },
          "engine": { "type": "string", "enum": ["standard", "neural", "long-form", "generative"] },
          "accessKeyId": { "type": "string" },
          "secretAccessKey": { "type": "string" }
        }
      },
      "edge": {
        "type": "object",
        "properties": {
          "voice": { "type": "string", "default": "de-DE-KatjaNeural" },
          "lang": { "type": "string", "default": "de-DE" },
          "outputFormat": { "type": "string", "default": "webm-24khz-16bit-mono-opus" },
          "rate": { "type": "string" },
          "pitch": { "type": "string" },
          "volume": { "type": "string" },
          "proxy": { "type": "string" },
          "timeoutMs": { "type": "number" }
        }
      },
      "kokoro": {
        "type": "object",
        "properties": {
          "voice": { "type": "string", "default": "af_heart", "description": "af_heart, af_bella, af_nicole, etc." },
          "modelId": { "type": "string" },
          "dtype": { "type": "string", "enum": ["fp32", "fp16", "q8", "q4", "q4f16"], "default": "fp32" }
        }
      },
      "elevenlabs": {
        "type": "object",
        "properties": {
          "apiKey": { "type": "string" },
          "voiceId": { "type": "string" },
          "modelId": {
            "type": "string",
            "default": "eleven_turbo_v2_5",
            "description": "turbo, flash, v2, v3, or full model ID"
          }
        }
      },
      "deepgram": {
        "type": "object",
        "properties": {
          "apiKey": { "type": "string" },
          "model": { "type": "string", "default": "nova-2" },
          "ttsModel": { "type": "string", "default": "aura-asteria-en" }
        }
      },
      "wyomingWhisper": {
        "type": "object",
        "properties": {
          "host": { "type": "string", "default": "127.0.0.1" },
          "port": { "type": "number", "default": 10300 },
          "uri": { "type": "string" },
          "language": { "type": "string" },
          "connectTimeoutMs": { "type": "number", "default": 10000 }
        },
        "description": "Wyoming Faster Whisper (remote STT over TCP)"
      },
      "localWhisper": {
        "type": "object",
        "properties": { "model": { "type": "string" }, "quantized": { "type": "boolean" } },
        "description": "Local Whisper STT (Xenova)"
      }
    }
  },
  "uiHints": {
    "enabled": {
      "label": "Enable Discord Voice",
      "help": "Enable real-time voice conversations in Discord voice channels"
    },
    "sttProvider": {
      "label": "Speech-to-Text Provider",
      "help": "whisper, gpt4o-mini, gpt4o-transcribe, gpt4o-transcribe-diarize (OpenAI), or deepgram"
    },
    "ttsProvider": {
      "label": "Text-to-Speech Provider",
      "help": "openai, elevenlabs, deepgram, polly, edge, or kokoro"
    },
    "ttsVoice": {
      "label": "TTS Voice (deprecated)",
      "help": "Use openai.voice, elevenlabs.voiceId, kokoro.voice instead"
    },
    "openai.voice": {
      "label": "OpenAI TTS Voice",
      "help": "nova, shimmer, echo, onyx, fable, alloy, ash, sage, coral"
    },
    "kokoro.voice": { "label": "Kokoro TTS Voice", "help": "af_heart, af_bella, af_nicole, etc." },
    "vadSensitivity": { "label": "VAD Sensitivity", "help": "Voice activity detection sensitivity (low/medium/high)" },
    "allowedUsers": { "label": "Allowed Users", "help": "Discord user IDs allowed to use voice (empty = all allowed)" },
    "openai.apiKey": { "label": "OpenAI API Key", "sensitive": true },
    "elevenlabs.apiKey": { "label": "ElevenLabs API Key", "sensitive": true },
    "elevenlabs.modelId": { "label": "ElevenLabs Model", "help": "turbo, flash, v2, v3 (or full model ID)" },
    "thinkingSound.enabled": { "label": "Thinking Sound", "help": "Play sound while processing" },
    "thinkingSound.path": { "label": "Thinking Sound File", "help": "Path to MP3" },
    "thinkingSound.volume": { "label": "Thinking Sound Volume", "help": "Volume 0-1" },
    "deepgram.apiKey": { "label": "Deepgram API Key", "sensitive": true }
  }
}