YouTube Sponsor Detection
Find sponsor reads in video transcripts and audio with typed Jev decisions.
What Jev decides
Which transcript line marks a boundary, or whether heard audio is a sponsor read.
A browser extension identifies sponsor-read boundaries with Jev, maps selected transcript lines back to timestamps, and offers manual or automatic skipping.
- Jev role
- Identify sponsor-read content and boundaries from transcript or transcribed audio.
- Input
- Numbered transcript lines or speech-to-text output with a sponsor definition.
- Output
- Line-ID Choices and yes/no probabilities.
- Decision frequency
- During transcript scanning and, in audio modes, while monitoring playback.
- Fallback
- Code converts line IDs to time; uncertain segments wait or require the configured threshold.
How it works
Overview
Sponsor Skip includes a Chrome extension and a small web app. Transcript mode sends numbered caption lines to Jev, which identifies sponsor-read boundaries. Code maps the chosen line IDs to timestamps and handles playback. Smart and Listen modes also use Deepgram transcription to confirm or find reads from audio.
Transcript mode needs captions and a TypeSafe key; audio modes additionally need Deepgram. The extension uses a confidence threshold before automatic skips, and its author-reported operating costs depend on mode. Jev does not generate timestamps directly.
- Language
- JavaScript
- Author
- trungdq88
Sources
Related projects
Jev Voice Browser
A browser that starts resolving voice commands while the user is still speaking.
What Jev decides
What the user intends, which page target it applies to, whether the command is complete, and whether it is destructive.
Jev × WebMCP
Turn WebMCP schemas and user wording into inspectable browser tool calls with typed Jev decisions.
What Jev decides
Which tool fits, which allowed value each typed parameter should take, and whether optional values were actually stated.
jev-turbo
Choose browser actions from named page controls and check whether a goal is done.
What Jev decides
Which visible control or navigation action to use next, and whether the goal is met.