Gemini Omni 1.2 Flash: Video with Native Audio, in One Pass

Generate Video With Native Audio

Generate video and audio together in the same pass, so your visuals and sound are created as one result. Build scenes with audio from the start instead of adding it separately after generation.

Choose How You Guide Your Video

Switch between Frame to Video and Reference to Video depending on how you want to control the result. Use specific frames to shape the beginning and end of a shot, or use visual references to guide the overall direction.

Control the Start and End of Your Shot

Add a start image, an end image, or both to guide how your shot begins and finishes. When both are provided, Gemini Omni 1.2 Flash generates the movement between them.

Guide With Up to 7 Images and a Video

Add up to 7 reference images and one reference video to guide characters, visual style, and motion. Give the model more visual context when you want consistency without defining specific start and end frames.

Generate Up to 4K

Choose from 360p, 720p, 1080p, or 4K depending on the output you need. Generate at lower resolutions when appropriate or move up to 4K for a more detailed final result.

Create Clips From 3 to 10 Seconds

Choose a duration from 3 to 10 seconds depending on the scene you want to create. Keep quick shots short or give actions and camera movement more time to develop in longer clips.