VoiceMode MCP

"Voice Mode for Claude Code (and other AI Coding Assistants)"

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.

See It In Action

Quick Start

# Install VoiceMode MCP python package and dependencies

curl -LsSf https://astral.sh/uv/install.sh | sh

uvx voice-mode-install

# Optional: Set OpenAI API key (backup if local services unavailable)

export OPENAI_API_KEY=your-openai-key

# Add VoiceMode to Claude

claude mcp add --scope user voicemode -- uvx --refresh voice-mode

# Start a voice conversation

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.

# Install local speech-to-text (Whisper)

voicemode whisper install

# Install local text-to-speech (Kokoro)

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)

Resources

GitHub Repository PyPI Package Report Issues