Best for
- Claude Code users who want to speak to their coding assistant
- Developers who need hands-free interaction during tasks
- Users who prefer local, private speech processing
V
VoiceMode
Community
Natural voice conversations with Claude Code and other MCP-capable AI assistants.
GitHub source repository ↗
56FMRS · C
VoiceMode is a practical MCP server that adds natural voice interaction to Claude Code. It supports both cloud and local speech processing, with sensible defaults like silence detection. Setup is straightforward via the provided installer, and it is well-suited for hands-free coding workflows. Privacy-conscious users should note that cloud STT/TTS sends audio to third-party servers, while local models require substantial system resources. Overall, it is a mature and actively maintained open-source project.
VoiceMode is an MCP server that brings natural voice conversations to Claude Code and other MCP-capable agents. It provides speech-to-text and text-to-speech via the MCP protocol, with optional local models (Whisper, Kokoro) or cloud services (OpenAI). It features low latency, smart silence detection, and works offline when local services are installed.
Tools
converse
Start a natural voice conversation with the AI assistant.
service
Manage the VoiceMode voice service.
Setup
- Install the UV package manager if needed: curl -LsSf https://astral.sh/uv/install.sh | sh
- Run the installer: uvx voice-mode-install
- Add to Claude Code: claude mcp add --scope user voicemode -- uvx --refresh --from voice-mode voicemode-mcp-launcher
- Optionally set OPENAI_API_KEY for cloud services.
- Start a conversation: claude converse
claude_desktop_config.json
{
"mcpServers": {
"voicemode": {
"command": "uvx",
"args": ["--refresh", "--from", "voice-mode", "voicemode-mcp-launcher"]
}
}
}
Fit and risk
Not for
- Users without a microphone or speakers
- Text-only environments where audio is not available
Required permissions
- Microphone access for capturing voice input
- Speakers or audio output devices for playing responses
- Network access when using cloud STT/TTS services (e.g., OpenAI)
- Claude Code MCP permissions for the converse and service tools
Risks and side effects
- When cloud speech services are enabled, audio is transmitted to third-party servers (e.g., OpenAI)
- Local speech models (Whisper, Kokoro) can be resource-intensive
- Microphone access means the MCP process captures ambient audio
Troubleshooting
- No microphone access: Check terminal/app permissions. On WSL2, install pulseaudio packages.
- UV not found: Run curl -LsSf https://astral.sh/uv/install.sh | sh.
- OpenAI API error: Verify that OPENAI_API_KEY is set correctly.
- No audio output: Check system audio settings and available devices.
Use cases
Walking to a meeting while keeping up with work
Cooking while debugging code
Giving your eyes a break after long screen time
Holding a coffee or a dog while coding
Hands-free operation when typing isn't possible
Supported clients
Claude CodeFull support