Local speech recognition MCP server powered by FunASR and SenseVoice. It provides privacy-friendly audio transcription through a transcribe_audio tool.
MCP server for audio transcription with speaker diarization. Transcribes MP3/WAV files using Faster-Whisper and pyannote.audio, outputs markdown with speaker labels, timestamps, summaries, and action items.
MCP server for audio transcription using local faster-whisper or OpenAI Whisper API, enabling multilingual transcription with optional GPT post-processing.