- Transcribe an audio file into individual words.
- Display and interact with each word’s start and end positions on a timeline or within the "Review Dashboard."
- Adjust timing offsets for the beginning and end of each word either globally or individually.
- Play full audio or specific words directly from within the app.
- Export words as separate `.wav` audio files.
- Record the timeline position, along with the global and per‑word timing offsets for each exported word, into a cutTemplate.txt file so that the individual words can later be played using only the source audio file.
GitHub repository: https://github.com/Northstrix/bootleg-text-slicer
Successfully tested with English and Italian audio files.
Both scripts work, but I wouldn’t advise you to use Bootleg Text Slicer V2.py to transcribe more than 60–90 seconds at a time. Otherwise, its UI might become laggy. You can easily adjust the transcription duration by moving the start and end sliders below the timeline.
Project Samples
