Descript reimagines audio and video editing with a deceptively simple insight: editing spoken-word media by manipulating a transcript is faster, more intuitive, and more accessible than traditional timeline editing. When you import audio or video into Descript, it produces an accurate transcript using AI. From that point, editing the media is as simple as editing a text document: highlight and delete a sentence to cut it from the recording, reorder paragraphs to restructure content, type new text to generate AI voice that sounds like the original speaker. Overdub is Descript's AI voice cloning feature. After training on a sample of your voice, Overdub generates new audio in your voice from typed text — useful for correcting mistakes, inserting new sentences, or updating outdated content in a recording without re-recording. Beyond transcript-based editing, Descript includes a full multitrack timeline editor, automatic filler word removal (with the same text-editing approach), screen recording, captions, stock media library, and video publishing tools. For podcasters, Descript eliminates the DAW learning curve entirely. For video creators, it dramatically speeds up the editing of talking-head interviews and educational content. For marketing teams, it enables non-technical staff to edit video content independently. Descript is used by major podcast networks, YouTube creators, enterprise marketing teams, and individual creators who want professional audio and video editing without professional complexity.