Source: deepmind.google/blog/gemini-omni-12-flash-fast-and-cost-effective-with-longer-clips
The new version raises the maximum clip length from 10 seconds in Omni 1.1 to 15 seconds, and duration can be set in one-second steps from 3 to 15 seconds. Google says developers can draft at 360p or 720p, fix details with follow-up edits instead of regenerating the whole clip, and then upscale finished clips to 1080p or 4K.
Google also highlights reference adherence and consistency. The model accepts character, product or style images, motion clips of up to three seconds, and audio cues, and it is described as keeping faces, garments and brand colors steady across camera angles. Multi-turn editing lets users change a product, background, lighting or aspect ratio in later turns without starting over.
Provisioned Throughput is available on Google Cloud, and outputs carry an imperceptible SynthID watermark. The model also powers features in Flow, Google Vids, Gemini for business and Google Ads, while the Gemini app is rolling out 15-second video creation to Google AI Ultra subscribers.
Why it matters if you build agents
Developers building video generation into agents can now request 15-second clips and refine them with follow-up edits rather than regenerating full clips each time. The lower price of $0.07 per second at 720p makes drafting and iteration cheaper to run at volume. Teams planning production pipelines should check the Provisioned Throughput option and the SynthID watermark on outputs.
Get stories like this every weekday
One short email with the day's agent tooling news.