Skip to main content
Glama
JWitcoff

Claude Voice Commands

by JWitcoff
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Claude Voice Commands

Enable natural voice interaction with Claude Code through MCP (Model Context Protocol).

Features

  • 🎤 Voice-to-text commands - Speak naturally to Claude Code

  • 🔊 Wake word activation - "Hey Claude" to start listening

  • 🚀 Low latency - Sub-second response with Google Speech Recognition

  • 🔄 Multiple backends - Google, Whisper, and OpenAI Realtime support

  • 📝 Command queue - Handle multiple rapid commands

  • 🛡️ Privacy-focused - Only listens when activated

Quick Start

Prerequisites

  • Python 3.8+

  • macOS, Windows, or Linux

  • Working microphone

  • Claude Desktop app

Installation

  1. Clone the repository:

git clone https://github.com/JWitcoff/Claude_Chat.git cd Claude_Chat

  1. Create virtual environment:

python3 -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate

  1. Install dependencies:

pip install -r requirements.txt

  1. Test your microphone:

python tests/test_microphone.py

  1. Configure Claude Desktop (Sprint 2+): Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{ "mcpServers": { "voice-commands": { "command": "python", "args": ["-m", "mcp_server.voice_server"], "cwd": "/path/to/Claude_Chat", "env": { "PYTHONPATH": "/path/to/Claude_Chat" } } } }

  1. Restart Claude Desktop

Usage

Basic Commands

Say to Claude Code:

  • "Activate voice mode" - Start continuous listening

  • "Stop voice mode" - Stop listening

  • "Hey Claude, [command]" - Wake word activation

Example Interactions

You: "Activate voice mode" Claude: ✅ Voice mode activated You: "Create a Python function to sort a list" Claude: [Creates the function] You: "Now add error handling to it" Claude: [Modifies the code] You: "Stop voice mode" Claude: ✅ Voice mode deactivated

Configuration

Create a .env file:

# Recognition Settings VOICE_BACKEND=google # Primary: google, whisper, openai VOICE_ENERGY_THRESHOLD=4000 # Microphone sensitivity WAKE_WORDS=hey claude,claude # Optional API Keys (for premium features) OPENAI_API_KEY=sk-... # For ultra-low latency

Development

See ROADMAP.md for the development plan and CLAUDE.md for Claude Code guidance.

Current Status

  • Sprint 0: Project Setup ✅

  • Sprint 1: Basic Voice Capture (In Progress)

Troubleshooting

Microphone Issues

# List available microphones python -c "import speech_recognition as sr; print(sr.Microphone.list_microphone_names())" # Calibrate for ambient noise python tests/calibrate_mic.py

Recognition Issues

  • Speak clearly and at normal pace

  • Reduce background noise

  • Adjust VOICE_ENERGY_THRESHOLD in .env

License

MIT

Contributing

See CONTRIBUTING.md for guidelines.

Acknowledgments

  • Google Speech Recognition API

  • OpenAI Whisper

  • FastMCP for MCP integration

This server cannot be installed

-
security - not tested
F
license - not found
-
quality - not tested

How are these scores calculated?

Resources

New MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/JWitcoff/Claude_Chat'

If you have feedback or need assistance with the MCP directory API, please join our Discord server