TokScript transcribes spoken dialogue and vocal content, separating it from background music. If a video has someone speaking over music, you'll get the speech transcribed; the background track is ignored.

If a video is purely music with no speech, the transcript will be empty or very minimal.

This works well for TikTok videos (which usually have people talking), reels (mix of speech and music), and YouTube. Some videos are music-only or have heavy music overlap, and those naturally produce shorter transcripts.

Was this helpful?