Gemini Omni 1.2 Flash generates 15-second video

Google's 5 November 2026 post launches Gemini Omni 1.2 Flash and says it is generally available across the Gemini API and Gemini for business. Native video goes to 15 seconds, up from 10 seconds on Omni 1.1, and duration can be set in one-second steps from 3 to 15 seconds. The same clip can be edited turn by turn, including a product, a background, lighting, or aspect ratio. Google says reference images, motion clips up to three seconds, and audio cues can guide a generation. The post says 720p video is $0.07 per second, 30% less than Omni 1.1. You can draft at 360p or 720p and upscale to 1080p or 4K. Outputs carry a SynthID watermark, and Provisioned Throughput is available.

The post says the model is rolling out in Google AI Studio and the Gemini API, in the Google Cloud console, in Flow, in Google Vids at no additional cost with a Google account or Workspace subscription, in the Gemini app for Google AI Ultra subscribers, and in Google Ads. Google says work continues on fast sports action, rapid script changes, and complex physics.

Who it's for: a developer or a team already generating short video in Gemini who wants a longer clip, a follow-up edit, or the lower 720p price.

Fits: Best for Video stays Runway, then Kling, then Luma, then Google Veo, then Pika. Omni 1.2 is a fast conversational clip. Veo's rank is still the realism ceiling when a generation comes back. Runway is still where you finish and aim a shot. A longer clip and a lower price leave that split where it is. The video guide and the Runway alternatives are unchanged. The verdict is unchanged.