Descript

Descript invented a new editing paradigm: you edit video and audio by editing text. Record an interview, upload a podcast, or capture a screen recording — Descript transcribes it automatically, then presents you with a word-for-word text document. Delete a sentence in the text, and the corresponding audio and video disappear from the recording. Reorder paragraphs in the transcript, and the video clips reorder on the timeline. Move words around, and the pacing of the recording changes.

For anyone who has spent hours in a traditional audio editor scrubbing waveforms to find and cut filler words, this is a revelation. Descript’s AI can automatically identify every “um,” “uh,” “like,” and “you know” across an entire recording and remove them all with a single click — a task that traditionally takes hours of tedious listening now takes seconds.

Overdub is Descript’s voice cloning feature, and it’s particularly valuable for fixing mistakes without re-recording. Train Overdub on your voice using a few minutes of audio, and from then on you can correct mispronounced words, add missed sentences, or fix stumbled phrases by simply typing the correct text. Descript synthesizes your cloned voice speaking the correction and drops it seamlessly into the recording.

For podcasters, Descript has become the standard tool. The workflow — record, transcribe, edit text, export — eliminates the traditional barrier to entry of learning audio editing software. For video creators, the screen recorder with automatic transcription and the social clips feature (which AI-selects highlight moments from longer recordings) make it a complete content production system.

The free tier is functional but limited on transcription hours. The Creator plan ($24/month) gives 10 hours of transcription monthly with Overdub access. Descript Pro ($40/month) removes transcription caps entirely.