gemini-omni-video
Gemini Omni Video is Google's text to video model, available here through a single relay API. It generates a short video clip from a written description. It takes a text prompt as input. Requests run server-side against 97AI.PRO with your credit balance, so you get Google quality without managing a separate Google account or key.
Video prompt describing content, style, camera language, or actions
Array of reference image URLs (max 7, each <=20MB)
Audio IDs from gemini-omni-audio for narration/dialogue (max 3)
Source video clips with trim ranges (max 1, <=100MB, <=30s)
Character IDs from gemini-omni-character API (max 3)
Generated video duration in seconds
Video aspect ratio (16:9 landscape, 9:16 portrait)
Random seed [0, 2147483647] for reproducibility
Output video resolution
