Descript capabilities
13 mapped capabilities, each graded and dated. The map shows what Descript can do; the audit shows whether it’s worth consolidating — and a guide shows how to move.
Capabilities
AI social clips and content repurposing
provisionalverified ~2 months agoAutomatically finds high-engagement moments in long recordings and turns them into ready-to-share vertical clips, plus derived assets like descriptions and chapters.
Automatic transcription
provisionalverified ~2 months agoAutomatically converts uploaded or recorded audio and video into a searchable, speaker-labeled, editable text transcript.
Captions and subtitles
provisionalverified ~2 months agoAuto-generates styled, animated on-screen captions and exportable subtitle tracks from the transcript.
Descript API and MCP connector for Claude/ChatGPT
provisionalverified 25 days agoA public API (open beta) plus a Model Context Protocol (MCP) connector that lets Descript be driven through natural-language conversation from Claude or ChatGPT, in addition to direct HTTP access, a CLI, and a Zapier integration. This gives Descript an API/integrations surface it previously lacked entirely.
Export and publishing
provisionalverified ~2 months agoExports finished projects to local video/audio/GIF files or shareable web links, and publishes podcasts to hosting destinations.
Eye Contact correction
provisionalverified ~2 months agoAI adjusts the speaker's gaze to appear to look directly at the camera even when they were reading off-screen notes.
Filler word and silence removal
provisionalverified ~2 months agoDetects and removes verbal fillers (um, uh, like, you know) and dead-air silences across a recording in one action.
Overdub and Regenerate AI voice cloning
provisionalverified ~2 months agoClones a user's voice so corrections can be made by typing, and regenerates audio (and matching lip movement) without re-recording.
Plans and pricing
provisionalverified 26 days agoA free tier plus three self-serve seat-based paid tiers (Hobbyist, Creator, Business) and a custom Enterprise plan, differentiated by included media/transcription hours, monthly AI credits, export resolution, and team features. Annual billing is discounted roughly 23-33% versus monthly.
Screen, webcam, and remote recording
provisionalverified ~2 months agoRecords screen, webcam, and audio (separately or together) and supports remote multi-participant recording for podcasts and interviews.
Studio Sound audio enhancement
provisionalverified ~2 months agoOne-click AI audio cleanup that removes background noise, echo, and hiss while enhancing voice clarity to sound studio-recorded.
Text-based video and audio editing
provisionalverified ~2 months agoEdit video and audio by editing the transcript: deleting or rearranging words in the text removes or reorders the corresponding media, so editing footage works like editing a document.
Underlord AI co-editor
provisionalverified ~2 months agoAn agentic AI co-editor that performs editing tasks from typed, conversational instructions rather than one-off suggestions.