Small decisions. Interesting possibilities.Submit contentSubmit
YouTube sponsor skipper preview

YouTube sponsor skipper

Detect youtube sponsor segment with live audio and transcript powered by Jev

Added to Jevfast

How it uses Jev

In transcript mode, Jev judges transcript phrases and identifies sponsor-related lines; in audio modes, it judges whether heard utterances are part of a sponsor read. Application code resolves the segment timestamps and performs playback skips.

What Jev decides

Sponsor boundary requestExample answers · not a recorded Jev response · Source ↗
Question 1 · P01
YOUR APP
INSTRUCTION

Does the first transcript phrase belong to the sponsor segment?

STATE

The state contains a transcript phrase window, surrounding text, video title, and the line where the sponsor is named. P01 is the first generated phrase ID.

JEV · NOUL
YesNo

App workflow

  1. Select a mode

    Choose transcript-only, transcript with audio confirmation, or audio-only listening.

  2. Find candidate sponsor lines

    Render transcript segments as labeled lines and ask Jev to identify the line that starts or belongs to a sponsor read.

  3. Confirm in audio modes

    When using audio, send the heard utterances to Jev and apply the configured confidence threshold.

  4. Skip the segment

    Use the application’s timestamp logic to move playback past the identified read.

Why it is interesting

The tool keeps timestamps and playback actions in code; model judgments identify content, while transcript and audio modes provide different confirmation paths.