voicemode

Name: voicemode
Author: mbailey

Verified · voicemode.dev

MCP server by mbailey · updated 6 days ago · ★ 1.4k

Score 95

Natural voice conversations for AI assistants - STT/TTS via MCP voicemode is published by voicemode.dev from its verified domain in the official MCP Registry.

Install Add to Cursor Add to VS Code GitHub

Yours? Claim it

Works withClaude Code Claude Desktop Cursor Codex Gemini CLI VS Code Windsurf Antigravity CLI

Maintenance

Last commit 6 days ago

Licence

MIT: permissive, fine for commercial use

Quality

Clear description, published package or server URL, 1,405 stars, original repository

Security

Asks for administrator rights (sudo)

What you need

Setting	Needed	What it is
`OPENAI_API_KEY`Environment variable, secret	Optional	OpenAI API key for cloud-based STT/TTS (optional - local services can be installed)
`VOICEMODE_DEBUG`Environment variable	Optional	Enable debug mode with detailed logging (true/false)
`VOICEMODE_SKIP_TTS`Environment variable	Optional	Skip TTS and show text only for faster response (true/false)
`VOICEMODE_PREFER_LOCAL`Environment variable	Optional	Prefer local services over cloud when available (true/false, default: true)
`VOICEMODE_AUDIO_FORMAT`Environment variable	Optional	Audio format: pcm, mp3, wav, flac, aac, opus (default: pcm)
`VOICEMODE_WHISPER_MODEL`Environment variable	Optional	Whisper model: tiny, base, small, medium, large (default: base)
`VOICEMODE_DISABLE_SILENCE_DETECTION`Environment variable	Optional	Disable silence detection for continuous recording (true/false)

From the publisher's entry in the official MCP Registry. Required settings are already in the install config below as placeholders.

Install voicemode

Built from the published package, never by AI

claude mcp add voicemode -- uvx voice-mode

Run in your terminal. Add --scope user to use it in every project.

Step-by-step: install voicemode in Claude Code

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

Settings, Developer, Edit config. Paste into claude_desktop_config.json and restart.

Step-by-step: install voicemode in Claude Desktop

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

Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).

Step-by-step: install voicemode in Cursor

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

Add to .vscode/mcp.json. VS Code uses "servers", not "mcpServers".

Step-by-step: install voicemode in VS Code

codex mcp add voicemode -- uvx voice-mode

Step-by-step: install voicemode in Codex

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

Add to ~/.gemini/config/mcp_config.json (all projects) or .agents/mcp_config.json (this project).

Step-by-step: install voicemode in Antigravity CLI

gemini mcp add voicemode uvx voice-mode

Gemini CLI was replaced by Antigravity CLI in June 2026 and remains only for enterprise licences and paid API keys.

Step-by-step: install voicemode in Gemini CLI

MCP servers run with your permissions and can read what you give them access to. Some need an API key: check the README and add it under env in the voicemode block.

Weekly newsletter

Like voicemode? Get the best new MCP servers every week

The best new tools, security warnings before you install something risky, and one practical tip. Free, three minute read.

Security check

Asks for administrator rights (sudo)In README.md: sudo
Downloads a script from the internet and runs it (a well-known installer)In README.md: curl -LsSf https://astral.sh/uv/install.sh | sh

Checked automatically: README.md. This looks for known risky patterns and is not a full audit. How grades work

Alternatives to voicemode

All alternatives →

FunASRmodelscope

Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

AAA Local 21k

Remove AI Watermarkswiltodelta

Identify and remove AI watermarks and provenance metadata from your own images and video.

AAA Local 6.1k

Server Video Resource modelcontextprotocol

MCP App Server demonstrating video resources served as base64 blobs

AAA Local 3.0k

Server Sheet Music modelcontextprotocol

MCP App Server for rendering and playing sheet music from ABC notation

AAA Local 3.0k

FFmpegpollinations

Trim, convert, resize, compress, and remix audio and video.

AAB Remote 5.2k

Ffmpeg Skill kajisho5

Agent Skill that gives coding agents (Claude Code, Cursor, Codex) a local video editor: 42 FFmpeg tools with a machine-readable contract, contract-derived MCP server, FFmpeg capability detection, probe-first / verify-last workflow. Cut, join, silence remo

AAA Local 2.0k

voicemode vs FunASR voicemode vs Remove AI Watermarks voicemode vs Server Video Resource

voicemode: common questions

How do I install voicemode?

In Claude Code run claude mcp add voicemode -- uvx voice-mode. For Claude Desktop, Cursor and VS Code, paste the config shown above and restart. See the install guides.

Is voicemode the official server?

voicemode is published by voicemode.dev from its verified domain in the official MCP Registry.

Is voicemode free?

The code is published under the MIT licence. The service it connects to may have its own pricing.

Is voicemode safe to use?

It scores 95 of 100. Grades: maintenance A, licence A, quality A. Security check: grade C (asks for administrator rights (sudo)). Review the code before you install. How grades work.

What are alternatives to voicemode?

Similar MCP servers: FunASR, Remove AI Watermarks, Server Video Resource, Server Sheet Music.

Does voicemode work with ChatGPT?

Not directly. It runs locally, and ChatGPT only connects to remote servers with a URL. Use it in Claude Code, Claude Desktop, Cursor, VS Code or Codex.