MCP server for audio transcription using local faster-whisper or OpenAI Whisper API, enabling multilingual transcription with optional GPT post-processing.
Local speech transcription MCP server using faster-whisper. Supports transcription, translation to English, and output in JSON, text, SRT, and VTT formats.
MCP server for transcribing audio and generating structured customer requirement meeting minutes (including flowcharts) using Whisper and AI backends, with export to md/html/pdf/docx and model/settings management.