Open-source subtitle editor that uses speech recognition models to generate and proofread subtitles
Overview
- Purpose
- Open-source subtitle editor that uses speech recognition models to generate and proofread subtitles
- Category
- Video
- Official site
- https://github.com/SubtitleEdit/subtitleedit (opens in a new tab)
Main features
- Edits subtitle text and timing
- Generates subtitles with speech recognition engines such as Whisper
- Speech-to-text with local models
- Batch generation of SRT subtitles for further proofreading
Best for
Suited to creators with existing video who want a subtitle draft first, then adjust timing, line breaks and text line by line.
Things to know
- Speech recognition engines and models may need separate downloads; support varies by system and configuration
- Check proper nouns, punctuation and timing in automatic subtitles by hand
FAQ
- Can it generate subtitles locally?
- Yes. The official documentation lists several local speech recognition engines; first use usually requires installing or downloading a model.
- Can it process videos in batches?
- The official documentation lists a batch transcription mode that generates SRT files for videos.