Runs on: Linux • macOS • Windows (WSL) | Python: 3.10+
Overview
VoiceMode MCP brings natural voice conversations Claude Code and other AI coding assistants.
Built on the Model Context Protocol (MCP), it provides a clean, reliable interface for adding voice capabilities
to your AI workflows.
Quick Start
Option 1: Claude Code Plugin (Recommended)
claude plugin marketplace add mbailey/voicemode
claude plugin install voicemode@voicemode
/voicemode:install
/voicemode:converse
Option 2: Python Installer
curl -LsSf https://astral.sh/uv/install.sh | sh
uvx voice-mode-install
claude mcp add --scope user voicemode -- uvx --refresh voice-mode
claude converse
The voice-mode-install command automatically:
-
✓
Checks and installs system dependencies (PortAudio, FFmpeg, gcc, etc.)
-
✓
Installs VoiceMode MCP package via UV
-
✓
Configures shell completions for the voicemode CLI
-
✓
Sets up optional local STT/TTS services (Whisper, Kokoro)
-
✓
Validates the installation and provides next steps
For manual setup or detailed instructions, see the Getting Started Guide.
Optional
Self-Hosted Voice Services
For complete privacy, run speech recognition and text-to-speech locally instead of using OpenAI.
Both whisper.cpp and Kokoro-FastAPI provide OpenAI-compatible APIs for seamless integration.
voicemode whisper install
voicemode kokoro install
Features
Voice Conversations
Natural voice interactions with Claude through your microphone and speakers, airpods, etc
OpenAI Compatible
Works with OpenAI's API and compatible services for speech processing
Simple Integration
Clean MCP protocol implementation that works seamlessly with Claude Desktop
Requirements
- OpenAI API key (or self-hosted STT & TTS services)
- Microphone and speakers for voice I/O
- Python 3.8+ (handled by uvx)