Captions

Captions is a feature-rich AI video creation app designed specifically for content creators who produce talking-head and presentation-style video content for social media platforms. The app combines several AI capabilities that address common pain points in creator workflows, from caption generation to subtle but impactful enhancements like eye contact correction.

The app's automatic caption generation is its most-used feature — AI transcribes speech with high accuracy and creates animated, stylized captions that can be customized to match a creator's brand aesthetic. Multiple caption styles are available from minimalist subtitle-style to bold, attention-grabbing animated text that's become characteristic of viral social media content.

Eye contact correction is a distinctive and technically impressive feature that subtly adjusts the appearance of a speaker's eyes to make them look directly at the camera even when they're looking at a script, prompter, or notes. This creates a more engaging video where the creator appears to make direct eye contact with viewers, increasing the sense of connection.

The filler word removal feature automatically detects and removes 'um', 'uh', 'like', and other filler words from recordings, producing a cleaner, more professional result without manual editing. This single feature can dramatically improve the quality of casual recordings.

Captions also includes AI-generated B-roll suggestions, script teleprompter functionality, and AI coaching features that analyze delivery and provide suggestions for improving pacing, energy, and clarity. These coaching capabilities make the app valuable for creators looking to systematically improve their video performance.