SmartLittleApps/local-stt-mcp
A high-performance Model Context Protocol (MCP) server providing local speech-to-text transcription using whisper.cpp, optimized for Apple Silicon.
Implements speaker diarization for multi-speaker identification and automatic audio format conversion via ffmpeg, exposing tools through the MCP framework for integration with AI assistants and applications. Built in TypeScript with whisper.cpp's Apple Neural Engine acceleration, achieving 15x real-time processing speed while maintaining <2GB memory usage compared to alternatives like WhisperX.
No commits in the last 6 months.
Stars
11
Forks
6
Language
TypeScript
License
MIT
Category
Last pushed
Jun 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/SmartLittleApps/local-stt-mcp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kajidog/mcp-tts-voicevox
VOICEVOX MCP Server (MCP Apps対応)
blacktop/mcp-tts
MCP Server for Text to Speech
austenstone/myinstants-mcp
MCP server that lets your ai agent press sound buttons. it's not that deep.
marcindulak/stt-mcp-server-linux
Local speech-to-text MCP server for Tmux on Linux (for use not only with Claude Code)
k2wanko/voicepeak-mcp
MCP server for VOICEPEAK text-to-speech synthesis