Docs / source reviewed
Sponsor Skip
Locate and skip YouTube sponsor reads from transcripts
How this project uses Jev
- Input
- Numbered captions or recent text returned by an external speech-recognition service
- Jev decides
- Whether a sponsor read exists, its boundary lines and whether the current speech remains inside it
- Code executes
- Code maps lines to timestamps and the Chrome extension skips segments according to settings; audio modes use Deepgram for transcription
Evidence and limitations
Jev reads text rather than audio. Caption retrieval may break with YouTube changes, and stepped skipping can overshoot into content. Audio modes need another service. We did not test false skips or reproduce the author’s cost reports.
This project has not been run independently here. Author-reported results are not independently verified results.
Original sources
- https://github.com/trungdq88/youtube-sponsor-detection/blob/de01f0568d043035889a296a61ce21e0accc8b16/README.md ↗
- https://github.com/trungdq88/youtube-sponsor-detection/blob/de01f0568d043035889a296a61ce21e0accc8b16/extension/lib/jev.js ↗
- https://github.com/trungdq88/youtube-sponsor-detection/blob/de01f0568d043035889a296a61ce21e0accc8b16/extension/lib/live.js ↗