AutoSub

AutoSub is an open-source command-line tool that leverages speech recognition (via Google API) to convert audio/video into transcripts or subtitle files. Users install Python, run a simple command specifying input media, and retrieve SRT files. It supports language auto-detection, though advanced editing must be done in a separate subtitle editor. Ideal for developers or power users comfortable with CLI. While it lacks a GUI, AutoSub’s minimal overhead and free usage make it appealing to those seeking a straightforward transcription pipeline for closed captions.