Voice Recorder MCP Server

by DefiBax

Media & Content/Audio audio recording transcription MCP server Whisper Goose AI voice recognition

An MCP server designed for recording audio from a microphone and transcribing it using OpenAI's Whisper model. It can be used as a standalone server or integrated as a custom extension with Goose AI.

View on GitHub

Last updated: N/A

What is Voice Recorder MCP Server?

This is an MCP (Model Context Protocol) server that records audio from the default microphone and transcribes it to text using OpenAI's Whisper model. It's designed to be used either as a standalone server or as a custom extension for the Goose AI agent.

How to use Voice Recorder MCP Server?

The server can be run standalone using the voice-recorder-mcp command, optionally specifying the Whisper model and sample rate. It can also be integrated with Goose AI by adding a Command Line Extension and setting the command field to the path of the voice-recorder-mcp executable. The MCP Inspector can be used for testing.

Key features of Voice Recorder MCP Server

Records audio from the default microphone
Transcribes recordings using Whisper
Integrates with Goose AI agent as a custom extension
Includes prompts for common recording scenarios

Use cases of Voice Recorder MCP Server

Transcribing voice notes
Creating transcripts of meetings
Integrating voice commands into AI agents
Performing voice-based data entry

FAQ from Voice Recorder MCP Server

How do I fix 'No audio being recorded'?

Check your microphone permissions and settings.

What if I get model download errors?

Ensure you have a stable internet connection for the initial model download.

What if I have issues integrating with Goose?

Make sure the command path is correct.

How can I improve audio quality?

Try adjusting the sample rate (default: 16000).

What Whisper model should I use?

The base.en model is recommended for everyday use, while medium.en or large models provide higher accuracy for important recordings.