Google made Gemini Omni 1.2 Flash generally available with 15-second video clips

On November 5, 2026, Google made Gemini Omni 1.2 Flash, its video generation and editing model, generally available. Clips can now run up to 15 seconds, up from 10 seconds in Omni 1.1, set in one-second steps from 3 to 15. Developers can draft at 360p or 720p, refine a clip through follow-up instructions instead of regenerating it, and then upscale to 1080p or 4K.

The model takes character, product or style reference images, motion clips of up to three seconds and audio cues. Google says it holds faces, garments, packaging text and brand colors consistent across camera angles, and improves lip-sync and multi-speaker dialogue. The Gemini API changelog adds consistency across up to six reference images and doubled paid-tier rate limits, and says requests to gemini-omni-1.1-flash will route to the new model from December 3, 2026.

Price is $0.07 per second of 720p video, a 30% cut from Omni 1.1. The model is on the Gemini API in Google AI Studio, Vertex AI, Flow, Google Ads Asset Studio and the Gemini app for AI Ultra subscribers, and Google Vids offers 15-second clips at no extra cost to Google account and Workspace users. Outputs carry an imperceptible SynthID watermark.

Why it matters: putting a conversational video editor into Vids for free and into Ads tooling moves generated video from a novelty into routine office and marketing workflows.

What it does not show: the post contains no quantitative benchmarks, only side-by-side examples against Omni 1.1. Google itself lists fast sports action and complex physics as areas still being worked on.