Audio

Provides audio input/output capabilities for AI assistants by recording from microphones and playing audio through speakers.
  • python

8

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

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

You can use Audio MCP Server to give AI assistants, like Claude, access to your computer’s audio system. It lets you list microphones and speakers, record audio, play back recordings, and play audio files through your speakers, enabling natural voice interactions and audio-based workflows.

How to use

Use the server with an MCP client to perform practical audio tasks. Start by listing available audio devices to understand what your system exposes. Then you can record short audio clips from a microphone, play back the most recent recording, or play audio files through your speakers. These actions are exposed as tools you can invoke from your MCP client.

How to install

Prerequisites you need before installation include Python 3.8 or higher and hardware-enabled audio input/output devices.

# Install via Smithery
npx -y @smithery/cli install @GongRzhe/Audio-MCP-Server --client claude

Manual installation steps to set up Audio MCP Server locally:

# 1) Clone the project and enter the directory
git clone https://github.com/GongRzhe/Audio-MCP-Server.git
cd Audio-MCP-Server

# 2) Create a Python virtual environment and install 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 installation
python setup_mcp.py

Configuration guidance

If you want to connect this server to Claude Desktop, configure the MCP connection by specifying the Python command and script path, along with the Python path for the server module. The following example shows how to structure the MCP configuration for your environment.

{
  "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"
      }
    }
  }
}

Usage tips

After you set up the server, restart Claude Desktop. When the tool is ready, you’ll see a hammer icon in the input box indicating that audio tools are available. Try asking Claude to list microphones and speakers, record a short clip, or play back a recording.

Troubleshooting basics

If you encounter issues, verify that microphone and speaker devices are recognized by your operating system and that the correct output/input devices are selected. Ensure the server process has access to audio hardware and that your configuration paths are correct.

Available tools

list_audio_devices

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

record_audio

Records audio from your microphone with configurable duration and quality.

play_latest_recording

Plays back the most recently recorded audio.

play_audio

Plays an audio source or converts text to speech in the future.

play_audio_file

Plays an audio file through your speakers.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
Audio MCP Server - gongrzhe/audio-mcp-server | VeilStrat