What is the MCP Server used for?

The MCP Server is used for recording audio and transcribing it into text using OpenAI’s Whisper model. It can function as a standalone server or integrate with Goose AI Agent.

How does the MCP Server integrate with Goose AI?

The MCP Server can be added as a command-line extension in Goose AI, allowing users to leverage its transcription capabilities within the Goose AI environment.

What are the system requirements for running the MCP Server?

The MCP Server requires Python 3.12+, an audio input device (microphone), and a stable internet connection for initial model downloads.

Can I choose different Whisper models for transcription?

Yes, the MCP Server supports various Whisper model sizes, allowing users to choose based on speed, accuracy, and memory usage.

How do I troubleshoot common issues with the MCP Server?

Common issues can be resolved by checking microphone permissions, ensuring a stable internet connection, verifying command paths, and adjusting audio sample rates.