voicemode MCP server

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

Design, images and media ★ 1,389 GitHub starsv8.12.0Updated Jul 21, 2026

Install

PyPI (stdio)uvx voice-mode

JSON for apps that use an mcpServers block (Claude Desktop, Cursor and others):

{"mcpServers": {
  "voicemode": {
    "command": "uvx",
    "args": ["voice-mode"]
  }
}}

From the server's registry entry. Many servers also need an API key or other settings: check the repository's README before you run it.

About this server

Registry name	`dev.voicemode/voicemode`
Repository	github.com/mbailey/voicemode
Packages	pypi `voice-mode`
In the registry since	Jul 21, 2026
GitHub stars	1,389

Listed from the official MCP Registry. We have not reviewed or tested this server; a local server runs code on your machine, so read the repository first.

Use it with

AI agents whose docs say they support MCP.

OpenAI Codex Claude Code LangChain Pi OpenCode Cursor GitHub Copilot LangGraph AI SDK Strands Agents Lovable Replit Agent

Similar design, images and media servers

All design, images and media servers →

tldraw★ 50.8K Draw and visually collaborate with your agents on tldraw's canvas. screenpipe★ 21.9K Search your local screen recordings, audio transcripts, and computer activity from screenpipe. FunASR★ 20.6K Transcribe local audio with FunASR and SenseVoice using private, on-device inference. Figma-Context-MCP★ 16K Give your coding agent access to your Figma data. Implement designs in any framework in one-shot. Agent-Native Assets★ 7,084 Digital asset manager - upload, organize, search, and generate on-brand images and videos FFmpeg★ 5,180 Trim, convert, resize, compress, and remix audio and video.