Audio Interface

🚀 Audio MCP Server

An MCP (Model Context Protocol) server that provides audio input/output capabilities for AI assistants like Claude. This server enables Claude to interact with the computer's audio system, including recording from the microphone and playing audio through the speakers.

🚀 Quick Start

After setting up the server, restart Claude Desktop. You should see a hammer icon in the input box, indicating that the tool is available. Try asking Claude the following questions:

• "What are the available microphones and speakers on my system?"
• "Record 5 seconds of audio from my microphone."
• "Play back the recording."
• "Play an audio file through my computer."

✨ Features

• List audio devices: View all available microphones and speakers on your system.
• Record audio: Capture audio from any microphone with customizable duration and quality.
• Play back recordings: Play the most recently recorded content.
• Play audio files: Play audio files through your speakers.
• Text-to-speech: (Future implementation, coming soon)

📦 Installation

Prerequisites

• Python 3.8 or higher
• Audio input/output devices on your system

Steps

1. Clone this repository or download the files to your computer:

git clone https://github.com/GongRzhe/Audio-MCP-Server.git
cd Audio-MCP-Server

2. Create a virtual environment and install the dependencies:

# Windows
python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt

# macOS/Linux
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

3. Or use the included setup script to automate the installation:

python setup_mcp.py

📚 Documentation

Configuration

Claude Desktop Configuration

To use this server with Claude Desktop, add the following to your Claude Desktop configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "audio-interface": {
      "command": "/path/to/your/.venv/bin/python",
      "args": [
        "/path/to/your/audio_server.py"
      ],
      "env": {
        "PYTHONPATH": "/path/to/your/audio-mcp-server"
      }
    }
  }
}

Replace these paths with the actual paths on your system. The setup script will generate this configuration for you.

Available Tools

list_audio_devices

List all available audio input and output devices on your system.

record_audio

Record audio from your microphone.

Parameters:

• duration: Recording duration in seconds (default: 5)
• sample_rate: Sampling rate in Hertz (default: 44100)
• channels: Number of audio channels (default: 1)
• device_index: Specific input device index (default: system default)

play_latest_recording

Play the most recently recorded audio.

play_audio

Placeholder for text-to-speech functionality.

Parameters:

• text: Text to be converted to speech
• voice: Voice to use (default: "default")

play_audio_file

Play an audio file through your speakers.

Parameters:

• file_path: Path to the audio file
• device_index: Specific output device index (default: system default)

Troubleshooting

No devices found

If no audio devices are found, check the following:

• Your microphone and speakers are properly connected.
• The operating system recognizes these devices.
• You have the necessary permissions to access the audio devices.

Playback issues

If you encounter playback issues, check the following:

• Ensure that the device index used exists on your system.
• Verify that the audio file path is correct.
• Ensure that the audio file format is supported.

📄 License

This project is licensed under the MIT License.

With this server, you can easily integrate Claude with various audio functions, allowing it to interact with your computer more naturally.