GoogleGemini Omni
Gemini Omni 1.2 Flash
Gemini Omni 1.2 Flash is a stable video generation and editing API with native audio output.
What the release provides
It accepts text, images and video. Generated clips run 3–15 seconds at 24 fps, with resolutions through 4K. Editing accepts up to 15 seconds; extension uses a 10-second lookback. First/last-frame interpolation supports 3–10 seconds.Gemini Omni Flash official API documentation
How to use it well
Practical guidance. Plan the shot and its sound together. Review continuity, speech timing and scene changes in the actual rendered clip. Use a clear start and end state for an extension so the new segment has a specific visual task.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | gemini-omni-1.2-flash |