Gemini Omni Video
Gemini Omni Video — image-to-video with synchronized native audio. Supply one or more input images via image_urls and describe the transformation and sound design in prompt.
Pricing — fixed per generation, in tokens (USD at $0.02/token). 720p and 1080p share the same price:
| resolution | 4s | 6s | 8s | 10s |
|---|---|---|---|---|
| 720p / 1080p | 20.48 | 27.3 | 34.13 | 40.95 |
| 4k | 47.78 | 54.6 | 61.43 | 68.25 |
Returns an img_uuid; poll GET /api/v1/jobs/detail (or use custom_callback_url) to get the generated video.
Headers
Body
Model name. Must be gemini_omni_video.
gemini_omni_video Describe the transformation and sound design to apply to the input image(s).
4096Input image URLs (required, 1-7 images). Max 20MB each; jpeg/png/webp.
1 - 7 elementsVideo duration in seconds. Supported: 4, 6, 8, 10. Defaults to 8.
4, 6, 8, 10 Output video aspect ratio.
16:9, 9:16 Output video resolution. 720p and 1080p are priced the same; 4k costs more.
720p, 1080p, 4k Optional random seed for reproducibility. If omitted, the model picks one automatically.
0 <= x <= 2147483647Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt.
"https://your-server.com/goenhance/callback"
