Skip to main content

Steps

1

Browse available styles

List all visual styles to find one that fits:
Each style has an aspect_ratio — some are landscape (16:9), others portrait (9:16). Use --human for a readable table view.
Each style includes a preview_video_url and thumbnail_url — open them to preview the visual treatment before choosing.
2

Generate a styled video

Pass the style_id along with your prompt:
The agent picks the avatar, voice, and layout. The style controls the visual treatment.To override the agent’s choices, pass additional flags:
3

Wait and download

Batch: same content, multiple styles

Generate the same prompt across different visual styles:

Interactive sessions for iteration

Review and refine before generating:

Available flags