Descript

Descript is a text-based video and podcast editor that turns your recordings into transcripts so you can cut, rearrange, and enhance audio/video as easily as editing a document, with AI tools for sound cleanup, overdubs, clips, and more.
​
Core features:
Automatic transcription of audio and video with editable text linked to the media timeline.
​Text-based editing: delete words, sentences, or sections in the transcript to edit the underlying media.
​Multitrack audio and video editing with a visual timeline for fine control.
​AI tools such as Studio Sound, Eye Contact, Green Screen, and filler word removal.
​Screen recording, remote recording, and webcam capture for tutorials, webinars, and interviews.
​Automatic captions, subtitles, and translations into multiple languages.
​
Key tools it offers:
Underlord AI assistant to clean up scripts, summarize content, and generate titles, descriptions, and social posts from your projects.
​Overdub for AI voice cloning and text-to-speech corrections in your own voice.
​Studio Sound for one-click noise reduction and voice enhancements.
Eye Contact and Green Screen to fix gaze and change backgrounds without reshooting.
AI Clips and highlight generation to repurpose long-form content into short-form reels and promotional snippets.​
​
Benefits for users
For podcasters & video creators: Dramatically speed up editing by cutting mistakes, filler words, and segments through text, while using AI to polish audio and video quality.
For marketers & educators: Quickly turn recordings into repurposed assets—blogs, show notes, shorts, and social posts—without needing separate tools or specialist editors.
For teams & agencies: Collaborate live on projects with commenting, version history, and shared workspaces, keeping production centralized and consistent.