voicemode
Natural voice conversations for AI assistants - STT/TTS via MCP
claude mcp add voicemode -- uvx voice-modeHow to start
- Run the command in your terminal, in the project where you want it.
- Sign in if asked the first time Claude connects.
- Check it: run
/mcpin Claude Code and look for it in the list.
What it needs
OPENAI_API_KEYOptional. Secret: keep it out of your repo. OpenAI API key for cloud-based STT/TTS (optional - local services can be installed)VOICEMODE_DEBUGOptional. Enable debug mode with detailed logging (true/false)VOICEMODE_SKIP_TTSOptional. Skip TTS and show text only for faster response (true/false)VOICEMODE_PREFER_LOCALOptional. Prefer local services over cloud when available (true/false, default: true)VOICEMODE_AUDIO_FORMATOptional. Audio format: pcm, mp3, wav, flac, aac, opus (default: pcm)VOICEMODE_WHISPER_MODELOptional. Whisper model: tiny, base, small, medium, large (default: base)VOICEMODE_DISABLE_SILENCE_DETECTIONOptional. Disable silence detection for continuous recording (true/false)
Environment variables as listed in the server's MCP Registry entry.
More in Local MCP servers
See all →Scrapling MCP Server
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
Chrome DevTools MCP
MCP server for Chrome DevTools
Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Next AI Draw.io
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Figma-Context-MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Windows-MCP
An MCP Server for computer-use in Windows OS