Descript

Converts uploaded video and audio files into editable text transcripts using a cloud-based transcription engine that supports 25 languages and automatically detects and labels 8+ speakers. The system processes media asynchronously and returns speaker-labeled transcripts that serve as the primary editing interface, enabling users to search, quote, and edit content as plain text rather than manipulating timeline-based video.

Propagates edits made to the transcript back to the video timeline by regenerating video segments to match the edited text. When a user deletes a filler word, reorders sentences, or modifies speaker text, the system recalculates the video duration and mouth movements to match the new transcript, maintaining audio-visual synchronization without manual frame-by-frame adjustment. Implementation details (whether segment-based or full re-render) are undisclosed.

An AI agent that takes natural language directives (e.g., 'remove all filler words', 'add captions', 'generate B-roll for the intro') and automatically applies edits to the video project. Underlord operates on the transcript and video timeline, executing a sequence of editing operations based on user intent. The mechanism is unclear (prompt-based editing, automated timeline manipulation, or both), but it reduces manual editing friction by automating common tasks.

Enables multiple team members to edit the same video project simultaneously in real-time, with shared transcript, timeline, and commenting. Team members can see each other's edits, leave comments on specific sections, and resolve conflicts. This is available on Business tier+ and supports teams of up to 5 people (billed separately). The collaboration mechanism (operational transformation, CRDT, or other) is not disclosed.

Tracks and enforces quotas on media hours (video/audio imported or recorded) and AI credits (used for regeneration, B-roll generation, voice synthesis, etc.) on a per-user, per-month basis. Users have hard caps on media hours and AI credits; exceeding limits requires upgrading tier or purchasing top-ups. This is a consumption-based pricing model that incentivizes efficient editing and limits platform costs.

Exports edited video in multiple formats and resolutions optimized for different platforms (YouTube, TikTok, Instagram, etc.). Export resolution is tiered by subscription (720p free, 1080p hobbyist, 4K creator+). The system handles format conversion, aspect ratio adjustment, and platform-specific optimizations (e.g., vertical video for TikTok, square for Instagram). Export is asynchronous and queued; processing time is unknown.

Removes the background from video (green screen or automatic background detection) and replaces it with a selected background (solid color, image, or video). This is available on free tier and uses AI-based background segmentation to identify the subject and background, then applies the replacement. This is useful for creating professional-looking videos without a physical green screen or professional lighting setup.

Identifies and removes common filler words ('um', 'uh', 'like', 'you know', etc.) from transcripts and automatically deletes the corresponding audio/video segments. The system detects fillers during transcription and flags them in the transcript for one-click removal, or users can manually select fillers to delete. Removal is instant at the transcript level and regenerates video to match.

Automatically detects the speaker's eyes and face in video and synthesizes corrected eye contact to make the speaker appear to look directly at the camera. The system uses background removal and face synthesis techniques to adjust gaze direction without requiring the speaker to re-record. Implementation uses AI-based face detection and eye-gaze synthesis, likely leveraging generative models for realistic eye movement.

Applies AI-based audio processing to remove background noise, enhance voice clarity, and improve overall audio quality without requiring professional microphones or soundproofing. The system analyzes the audio track, identifies noise patterns, and applies noise suppression and voice enhancement filters. This is a cloud-based audio processing pipeline, not real-time; processing happens during video regeneration or export.

Clones the user's voice from a short audio sample and regenerates speech in the user's voice to match edited transcript text. The system uses voice synthesis and mouth-movement synthesis to create realistic video of the user speaking new or edited dialogue. This enables users to fix mistakes, add new sentences, or change wording without re-recording. Voice cloning requires a training sample (length unknown) and regeneration consumes AI credits.

Generates AI-created video clips (B-roll) that match the content of the transcript using text prompts and the latest generative video models. Users can specify what B-roll they want ('show a coffee cup', 'show a person typing') and the system generates realistic video clips to insert into the timeline. This is available on Creator tier+ and consumes AI credits. The underlying video generation model is not disclosed (could be Runway, Synthesia, or proprietary).

Creates a talking-head avatar from a user-provided photo or text description and generates video of the avatar speaking a provided script. The system synthesizes the avatar's appearance, voice, and mouth movements to create a realistic video of a virtual presenter. This is available on Creator tier+ (gallery avatars) or Business tier+ (custom avatars from photo/text). Avatars can be used to create videos without filming, enabling rapid content production.

Generates captions from the transcript and automatically positions and styles them on the video. Captions are created from the transcript text, synchronized to the audio, and can be customized with fonts, colors, animations, and positioning. This is available on all tiers and serves both accessibility and engagement purposes. Captions can be exported as separate files (SRT, VTT) or burned into the video.

Translates the transcript into 30+ languages and generates dubbed audio in the target language using voice synthesis. The system translates the transcript, synthesizes speech in the target language (using a voice similar to the original speaker or a selected voice), and regenerates video with the dubbed audio and synchronized mouth movements. This is available on Business tier+ and enables rapid localization without hiring translators or voice actors.