mcp_servers
If you are the rightful owner of mcp_servers and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
An MCP server for recording audio and transcribing it using OpenAI's Whisper model.
The Voice Recorder MCP Server is designed to facilitate audio recording and transcription using OpenAI's Whisper model. It can function as a standalone MCP server or integrate as a custom extension with the Goose AI agent. The server allows users to record audio from the default microphone and transcribe it into text, providing a seamless experience for various recording scenarios. It supports multiple Whisper model sizes, each optimized for different use cases, from quick transcriptions to critical recordings. The server is easy to install and configure, requiring Python 3.12+ and an audio input device. Users can adjust settings such as the Whisper model and audio sample rate to suit their needs. The server also offers tools for starting, stopping, and transcribing recordings, making it a versatile solution for audio transcription tasks.
Features
- Record audio from the default microphone
- Transcribe recordings using Whisper
- Integrates with Goose AI agent as a custom extension
- Includes prompts for common recording scenarios
Tools
start_recording
Start recording audio from the default microphone
stop_and_transcribe
Stop recording and transcribe the audio to text
record_and_transcribe
Record audio for a specified duration and transcribe it
