Skip to content
mcp/harbor
Grok

voicemode for Grok

dev.voicemode/voicemode

Natural voice conversations for AI assistants - STT/TTS via MCP

client:Grok transport:stdio runtime:pypi

Install voicemode in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "voicemode": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "voice-mode"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "VOICEMODE_DEBUG": "<VOICEMODE_DEBUG>",
        "VOICEMODE_SKIP_TTS": "<VOICEMODE_SKIP_TTS>",
        "VOICEMODE_PREFER_LOCAL": "<VOICEMODE_PREFER_LOCAL>",
        "VOICEMODE_AUDIO_FORMAT": "<VOICEMODE_AUDIO_FORMAT>",
        "VOICEMODE_WHISPER_MODEL": "<VOICEMODE_WHISPER_MODEL>",
        "VOICEMODE_DISABLE_SILENCE_DETECTION": "<VOICEMODE_DISABLE_SILENCE_DETECTION>"
      }
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

voicemode in other clients

voicemode MCP server