📝Auto Captions

Select "Auto Captions" to instantly generate animated captions.

Characters per caption

Choose how many characters appear in each caption.

Unique settings are saved for each Sequence aspect ratio: Landscape, Portrait, and Square.

Language

Select Auto to auto-detect the spoken language or choose a transcription language.

Selecting a transcription language speeds up processing time.

Single-word captions

Check this box to force Auto Captions to always split by word.

Also generate a Caption Track

Check this box to also create a new Caption Track.

Model

Choose from 5 transcription models with varying speed & accuracy (default Tiny).

Model details

Name	Size	Description
Tiny	41.5MB	Fastest model with basic accuracy.
Base	78MB	Balanced model offering good acccuracy and reasonable speed.
Small	262.2MB	High accuracy model with moderate speed.
Medium	785.2MB	Very high accuracy model with slower processing but excellent results.
Large v3 Turbo	833.7MB	Most accurate text transcription with slower processing time. Recommended for non-English languages.

Transcription models are saved in your machine's Documents folder. Delete and redownload models at any time.

Windows

C:\Users\*username*\Documents

MacOS

~/Users/*username*/Documents

VAD (Voice Activity Detection)

Choose from 4 presets for precise speech detection: Auto, Podcast, Monologue, Fast-paced. Choose Custom to dial in your own advanced controls.