Published on September 17, 2025, a Python command-line tool transcribes long audio and video through a speech-recognition API.
On September 17, 2025, a Python command-line tool for a speech-recognition API was presented. It transcribes long audio and video, splits content using voice activity detection (VAD), makes parallel calls, supports multiple media formats, and performs automatic resampling.
The announcement describes the scope and features but provides no performance metrics. To confirm details and compatibility, consult the original documentation and project; test with representative files before adopting the tool and check the transcript against the audio.