Audio transcription server that provides speech-to-text capabilities using OpenAI's Whisper API. Built with TypeScript and the MCP SDK, it exposes a tool for transcribing audio files with configurable language settings and optional file saving. Particularly valuable for users who need to convert spoken content to text through AI assistants while maintaining control over the transcription process and output format.
No reviews yet. Be the first to review!
Sign in to join the conversation
Transcribe audio files using OpenAI's API. Required parameter: filepath (string). Optional parameters: save_to_file (boolean to save transcription to a file), language (ISO-639-1 language code, e.g., 'en', 'es').
