The Audio MCP Server provides audio input/output capabilities for AI assistants like Claude, enabling them to interact with computer audio systems. Built with Python using sounddevice and soundfile libraries, it offers tools to list audio devices, record from microphones, play recordings, and handle audio files. The implementation includes features for device selection, customizable recording parameters, and temporary file management for audio storage. This server is particularly useful for voice interaction workflows, audio analysis, and creating more accessible AI experiences through spoken communication.
Lists all available audio input and output devices on your system.
Records audio from your microphone. Parameters: duration (int, default: 5), sample_rate (int, default: 44100), channels (int, default: 1), device_index (int, default: system default)
Plays back the most recently recorded audio.
Placeholder for text-to-speech functionality. Parameters: text (string), voice (string, default: 'default')
Plays an audio file through your speakers. Parameters: file_path (string), device_index (int, default: system default)
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AIOur bundler currently only supports TypeScript-based servers. Check back soon!