Voicemode
Voice conversations with Claude Code and other MCP agents using local or cloud speech
- Pricing
- Open source
- Platforms
- macOS, Linux, Windows
- Runs
- Locally
- Version
- 9.0.2
- Listing updated
- today
Similar MCP servers
About Voicemode
Voicemode is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.
The README frames voice as a way to stay available when typing is not practical, such as walking, cooking or giving your eyes a rest. The agent speaks its replies and listens through your microphone, and smart silence detection stops recording when you stop talking.
Speech can run entirely on your machine with Whisper.cpp for speech-to-text and Kokoro for text-to-speech, which expose the same API as OpenAI so the server switches between local and cloud. Local services are preferred by default, and an OpenAI key serves as a fallback. Settings include audio format, Whisper model size, a text-only mode and optional saving of audio for debugging.
It installs as a Claude Code plugin or through a Python installer package, and runs on Linux, macOS, Windows (native or WSL) and NixOS with Python 3.10 to 3.14. The permissions section names two tools, converse and service, that can be pre-approved to avoid prompts.
Install
Run in a terminal
claude mcp add voicemode --env OPENAI_API_KEY='<OPENAI_API_KEY>' -- uvx voice-modeAdd to claude_desktop_config.json
{
"mcpServers": {
"voicemode": {
"command": "uvx",
"args": [
"voice-mode"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"voicemode": {
"command": "uvx",
"args": [
"voice-mode"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"voicemode": {
"type": "stdio",
"command": "uvx",
"args": [
"voice-mode"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"voicemode": {
"command": "uvx",
"args": [
"voice-mode"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"voicemode": {
"command": "uvx",
"args": [
"voice-mode"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}Using several servers? Build one config file with the MCP config generator.
Configuration
OPENAI_API_KEYOpenAI API key for cloud-based STT/TTS (optional - local services can be installed)VOICEMODE_DEBUGEnable debug mode with detailed logging (true/false)VOICEMODE_SKIP_TTSSkip TTS and show text only for faster response (true/false)VOICEMODE_PREFER_LOCALPrefer local services over cloud when available (true/false, default: true)VOICEMODE_AUDIO_FORMATAudio format: pcm, mp3, wav, flac, aac, opus (default: pcm)VOICEMODE_WHISPER_MODELWhisper model: tiny, base, small, medium, large (default: base)VOICEMODE_DISABLE_SILENCE_DETECTIONDisable silence detection for continuous recording (true/false)
Tools this server provides (2)
Taken from the project documentation; the running server may differ.
- converse
- Starts a spoken conversation turn.
- service
- Manages local voice services.
What it does
- Spoken conversations
- Speaks agent replies and listens through the microphone.
- Local speech services
- Runs Whisper.cpp and Kokoro for offline use.
- Cloud fallback
- Uses an OpenAI key when local services are unavailable.
- Silence detection
- Stops recording when you stop speaking.
- Configurable audio
- Sets format, Whisper model size and text-only mode.
- Claude Code plugin
- Installs through the plugin marketplace.
Good for
- Talk through a coding task while walking or cooking
- Rest your eyes while an agent works
- Dictate instructions without typing
- Keep voice processing fully local for privacy
Pricing
Open source
MIT-licensed; cloud speech costs depend on your OpenAI usage
Voicemode FAQ
Does it work offline?
Yes, with the optional local Whisper.cpp and Kokoro services.
Do I need an OpenAI key?
Only if you want cloud speech; it is optional when local services are installed.
Which platforms are supported?
Linux, macOS, Windows (native or WSL) and NixOS.
What do I need?
A computer with a microphone and speakers.
Is Voicemode free?
Yes. Voicemode is open source, so you can use and self-host it for free.
How do I add Voicemode to Claude Code?
Run this command in your terminal: claude mcp add voicemode --env OPENAI_API_KEY='<OPENAI_API_KEY>' -- uvx voice-mode
What are the best alternatives to Voicemode?
The closest alternatives to Voicemode are REA, Context7, Chrome DevTools MCP, Codebase Memory and GitHub.
Where this comes from
- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.


