voice-to-text-mcp

acazau/voice-to-text-mcp

3.1

If you are the rightful owner of voice-to-text-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

A Model Context Protocol (MCP) server for voice-to-text transcription using Rust and OpenAI's Whisper with CUDA acceleration.

Tools

Functions exposed to the LLM to take actions

transcribe_file

Transcribe an audio file to text

start_recording

Begin live audio recording

stop_recording

Stop recording and get transcription

get_recording_status

Get current recording status

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources