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.
まだレビューはありません. 最初のレビューを投稿しましょう！
会話に参加するにはサインインしてください
Highlight AILists all available audio input and output devices on your system.
Records audio from your microphone. Parameters: duration (seconds, default: 5), sample_rate (Hz, default: 44100), channels (number, default: 1), device_index (specific input device index, default: system default).
Plays back the most recently recorded audio.
Placeholder for text-to-speech functionality. Parameters: text (the text to convert to speech), voice (the voice to use, default: 'default').
Plays an audio file through your speakers. Parameters: file_path (path to the audio file), device_index (specific output device index, default: system default).
