Edit video and audio by editing the transcript text. Includes filler-word removal and voice cloning for retakes.
Updated: July 2026
Descript changes the paradigm of video and audio editing: instead of working on a timeline, you edit the transcript text directly, and the video cuts and reorders itself. Saying “delete this paragraph” is literally deleting that text.
It also automatically detects and removes filler words (“um,” “like,” long silences), something that takes a huge amount of time in manual editing. The voice cloning feature (Overdub) lets you fix a recording mistake by typing the correction, without having to re-record.
It’s one of the most recommended tools for podcasters and video creators who produce spoken content frequently, where editing speed matters as much as the final result.