Gemini Omni Flash
In Omnibo, from 27.8 cr/s.

You give it

• A text prompt
• A start frame and an end frame
• Up to 6 reference images
• Up to 3 reference videos
• A clip of up to 15 seconds to edit
• A clip to extend

You get back

• A clip of 3 to 15 seconds
• In 360p, 720p, 1080p, and 4K
• In these shapes: 16:9 and 9:16
• With sound, always on

In Omnibo

1. Open Video in the app and pick Gemini Omni Flash in the model selector.
2. Choose a length from 3 to 15 seconds and a resolution: 360p, 720p, 1080p, and 4K.
3. Add a start frame or an end frame to pin how the clip opens or closes.
4. Attach references to steer it: images and videos.
5. To work on a clip you already have: edit and extend.

Try Gemini Omni Flash →

Over MCP

Connect Omnibo to your AI assistant over MCP, then call these tools with the model id gemini-omni-1.2-flash.

• list_models
• balance
• generate_video
• edit_video
• extend_video
• job_status
• wait_for_job

An example call to generate_video

{
  "model": "gemini-omni-1.2-flash",
  "prompt": "A slow push-in on a lighthouse at dusk, rain on the lens",
  "duration_seconds": 10,
  "resolution": "720p"
}

How to connect over MCP