Captions are styled subtitles that display your spoken script on screen. VideoGen generates captions automatically from your voiceover and lets you customize their appearance across the entire project.
What captions show
Captions display the text from your script as the voiceover plays. They appear word-by-word or phrase-by-phrase, synchronized to the audio.
For AI voiceover, captions come from your script text. For uploaded audio, captions come from the transcription.
The Captions tab
Open the Captions tab in the left sidebar to style your captions. This tab shows:
A live preview of your caption style
Style controls for font, color, size, and position
Preset styles to quickly apply common looks
Caption style options
You can customize:
Font: Choose from available fonts
Size and weight: Adjust text size and make it bold
Colors: Set fill and stroke colors for text
Spoken word highlight: Different color for the currently spoken word
Background: Add a background shape behind text (rectangle, wrapped, or word-by-word)
Alignment: Position captions top, middle, or bottom, and align left, center, or right
Caption presets
VideoGen includes preset styles like:
Classic: Clean, readable subtitles
Instagram, TikTok, YouTube Shorts: Social media-optimized styles
Bold & Classy, Fun: Stylized looks for different content
Select a preset to apply it instantly, then customize further if needed.
Show or hide captions per asset
You can turn captions on or off for individual clips:
Select an asset with voiceover in the timeline.
In the right panel, find the Captions toggle.
Switch it on or off.
This is useful when you want narration without visible text in certain sections.