Back
mediabrowser

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.

CHOICENOUL
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.
Author reported · Source reviewed

How it works

Input
Numbered transcript lines or speech-to-text output with a sponsor definition.
Jev
CHOICE + NOUL
Output
Line-ID Choices and yes/no probabilities.

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 checked Sep 23, 2026

Sources

Related projects