- Submit a YouTube URL using the form above. Any public YouTube video can be processed.
- Audio extraction - We download the audio track from the video for processing.
- Frame capture - Screenshots are taken at regular intervals throughout the video.
- AI transcription - The audio is transcribed using Whisper with high accuracy settings.
- Section alignment - Transcript sections are aligned with their corresponding frames.
- Browse the result - View the interactive transcript with synchronized frames and source annotations.
Processing typically takes 2-5 minutes depending on video length. You'll receive an email notification if you provided your address.