SkillFoxx

Type a name, a task or a service

VoiceMode

An MCP server for voice conversations with Claude Code and other MCP agents: speech recognition and voice synthesis, local or cloud

MCP serverOfficial

Medium risk

We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.

Why this level

  • Accesses the microphone and plays audio on the device
  • In cloud mode it sends audio to an external recognition and synthesis service
  • Installs and runs local speech services
All reasons and checks

mbailey/voicemodeAuthor:mbailey

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add mcp/voicemode

Detects the agents on your machine, checks the risk and pins the version.

Other ways to install

Run in a terminal

claude mcp add --transport stdio voicemode -- uvx voice-mode==8.12.0

Or add to the file .mcp.json, in the project

{
  "mcpServers": {
    "voicemode": {
      "command": "uvx",
      "args": [
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the mcpServers key.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

Install in Cursor

The button opens the agent and offers to add the server. If nothing happens, copy the config below.

Add to the file ~/.cursor/mcp.json, for all projects

{
  "mcpServers": {
    "voicemode": {
      "command": "uvx",
      "args": [
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the mcpServers key. For a single project, put the same block into .cursor/mcp.json.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

Install in VS Code

The button opens the agent and offers to add the server. If nothing happens, copy the config below.

Run in a terminal

code --add-mcp '{"name":"voicemode","type":"stdio","command":"uvx","args":["voice-mode==8.12.0"]}'

Or add to the file .vscode/mcp.json, in the project

{
  "servers": {
    "voicemode": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the servers key.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

Run in a terminal

codex mcp add voicemode -- uvx voice-mode==8.12.0

Or add to the file ~/.codex/config.toml, for all projects

[mcp_servers.voicemode]
command = "uvx"
args = ["voice-mode==8.12.0"]

If the file already exists, append the block to the end.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

Run in a terminal

gemini mcp add -s user voicemode uvx voice-mode==8.12.0

Or add to the file ~/.gemini/settings.json, for all projects

{
  "mcpServers": {
    "voicemode": {
      "command": "uvx",
      "args": [
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the mcpServers key.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

Add to the file ~/.config/devin/mcp_config.json, for all projects

{
  "mcpServers": {
    "voicemode": {
      "command": "uvx",
      "args": [
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the mcpServers key. Legacy Cascade keeps the MCP config in ~/.codeium/windsurf/mcp_config.json.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

Formerly Windsurf.

Add to the file cline_mcp_settings.json, for all projects

{
  "mcpServers": {
    "voicemode": {
      "command": "uvx",
      "args": [
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the mcpServers key. Open the settings file in Cline: MCP Servers tab, Configure MCP Servers.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

Add to the file .roo/mcp.json, in the project

{
  "mcpServers": {
    "voicemode": {
      "command": "uvx",
      "args": [
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the mcpServers key.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

A fork of Roo Code, same .roo folders.

Add to the file opencode.json, in the project

{
  "mcp": {
    "voicemode": {
      "type": "local",
      "command": [
        "uvx",
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the mcp key.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

Add to the file ~/.config/zed/settings.json, for all projects

{
  "context_servers": {
    "voicemode": {
      "command": "uvx",
      "args": [
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the context_servers key.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

Add to the file .codeassistant/mcp.json, in the project

{
  "mcpServers": {
    "voicemode": {
      "command": "uvx",
      "args": [
        "voice-mode==8.12.0"
      ]
    }
  }
}

If the file already exists, add the server inside the mcpServers key.

Keys and settings

OPENAI_API_KEYsecret, optional
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)

Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.

You will need: uv

Checked against the repository on Sep 25, 2026, commit 126d15e.

Text for your agent

For Claude Code: claude plugin marketplace add mbailey/voicemode, then claude plugin install voicemode@voicemode, then /voicemode:install and /voicemode:converse. As an MCP server: uvx voice-mode-install, then claude mcp add --scope user voicemode -- uvx --refresh --from voice-mode voicemode-mcp-launcher.

Other ways from the author
claude plugin marketplace add mbailey/voicemode
claude plugin install voicemode@voicemode

After install run /voicemode:install for dependencies and local services, then /voicemode:converse.

This is third-party code. Review the repository files before installing.

What it does

VoiceMode gives the agent a converse tool: you speak into the microphone and the agent answers by voice. Speech recognition and synthesis can run fully local via Whisper and Kokoro, or use cloud services behind an OpenAI-compatible API, and it switches between them transparently. It detects silence to stop recording when you pause and focuses on low latency so the exchange feels like a real conversation. The server installs as a Claude Code plugin or as an MCP server through uvx, and runs on Linux, macOS and Windows including WSL. The package is published on PyPI as voice-mode.

Who it is for. For developers who prefer to talk to the agent when their hands or eyes are busy.

Good fit when

  • You want to talk to Claude Code by voice instead of typing
  • You need to work with the agent away from the screen: on the move, while cooking, when your eyes are tired
  • You need local voice input and output without sending audio to the cloud

Not a fit when

  • There is no microphone or speakers, or the environment has no audio access
  • You only need text input and do not need voice

Example request

Let's switch to voice mode and talk through how to rewrite this module

Limitations

You need a working microphone and speakers. Local speech services need ffmpeg, portaudio and similar dependencies, plus disk space and compute for the models. The cloud path through OpenAI needs a key and is not reachable from Russia without a VPN, while the local mode works without one. On WSL2 microphone access needs the pulseaudio packages.

How to disable. Remove the plugin via /plugin or detach the MCP server with claude mcp remove voicemode. The local speech services can be stopped and removed separately.

MCP

Transport
stdio
Authentication
not required
Environment variables
OPENAI_API_KEY
secret		OpenAI key for cloud speech recognition and synthesis, optional; the local mode works without it.

Security check

  • Accesses the microphone and plays audio on the device
  • In cloud mode it sends audio to an external recognition and synthesis service
  • Installs and runs local speech services

README in short

The README presents VoiceMode as a way to hold voice conversations with Claude Code and other MCP agents. The quick start offers two paths: the Claude Code plugin via its marketplace, or installing the Python package and wiring the MCP server through uvx. Features include natural dialogue, offline use with local speech services, low latency, silence detection and a choice between local and cloud modes. Separate sections cover system dependencies per platform, permission setup, installing Whisper and Kokoro, and common audio problems. It is MIT licensed and the PyPI package is named voice-mode.

FAQ

Can it run offline without an OpenAI key?

Yes. With local Whisper and Kokoro the recognition and synthesis run on your machine. The OpenAI key is only for the cloud path and acts as a fallback.

Which agents does it work with?

The main path is the Claude Code plugin, but the server speaks the MCP protocol, so it also connects to other MCP-compatible agents.

Official

A self-hosted knowledge base with block-level references and a built-in MCP server for connecting AI agents to your notes

MCP serverMedium risk46.5K
Editors’ pick

A CLI for every Google Workspace API with JSON output and agent skills: Drive, Gmail, Calendar, Sheets and more

CLIHigh risk31.2K
Editors’ pick

Local search over Markdown notes, docs and meeting transcripts: keywords, semantic search and reranking, with an MCP server

CLIMedium riskNo VPN needed30.1K
Editors’ pick

A task manager for AI-driven development: breaks a PRD into dependent tasks and guides the agent through them via MCP or CLI

MCP serverMedium risk28.1K
Foxx AIVoiceMode

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.