Gemini Omni 1.2 Flash reaches GA with longer, cheaper video
Google's video-generation model moves to general availability with longer clips, 4K output and a 30% price cut, plus a mode to edit existing video without regenerating it.
Google made Gemini Omni 1.2 Flash generally available on 5 November, extending native video generation from 10 seconds to 15 and cutting price by 30%.
You can now set a clip’s length in one-second increments from 3 to 15 seconds, with resolution up to 4K, and the model renders synchronised audio with more natural dialogue, clearer lip-sync and distinct multi-speaker voices. 720p video now costs $0.07 a second. A new multi-turn editing mode lets you swap a background, product or aspect ratio on an existing clip without regenerating it from scratch, using reference images or motion clips of up to three seconds to keep characters and style consistent. It ships across the Gemini API, Google Cloud, Google Vids, Flow and Gemini for business, and is rolling out to AI Ultra subscribers in the Gemini app.
Why it matters: if you’re generating short video, product demos, social clips, ad creative, a 50% longer clip at 30% lower cost changes the budget math, and editing an existing clip instead of regenerating the whole thing cuts both cost and the chance a regeneration drifts off-brand.
The caveat: Google says fast sports action, rapid scene changes and complex physics are still rough. This is a Flash-tier model built for speed and cost, not physical accuracy.