Gemini Omni 1.2 Flash: 15-second video, 30% cheaper

What changed?

Google DeepMind released Gemini Omni 1.2 Flash today. Clips can now run natively up to 15 seconds (up from 10 with Omni 1.1), with duration set in one-second steps from 3 to 15 seconds. Pricing drops 30% versus Omni 1.1, to $0.07 per second for 720p video.

For the first time, Omni is generally available on the Gemini API and Google Cloud, with Provisioned Throughput. Outputs carry an imperceptible SynthID watermark.

Conversational editing and reference adherence

The most practical addition is multi-turn conversational editing: refine the same clip turn by turn (swap a product or background, change lighting, weather or aspect ratio) instead of regenerating it. This works across full 15-second clips.

You can guide generation with character, product or style images, short motion clips of up to three seconds and audio cues. Google says faces, garments, packaging typography and brand colors stay consistent across camera angles, with less drift and fewer unwanted jump cuts in continuous camera moves. Speech is more natural, lip-sync is clearer and multiple speakers can get distinct voices.

Why it matters

The cost workflow is the point: draft at 360p or 720p, fix details with a follow-up edit, then upscale the best take to 1080p or 4K. For ad and product video pipelines that cuts the price of iteration noticeably.

Google flags the limits itself: fast sports action, rapid script changes and complex physics are still being worked on. You can try it in Google AI Studio, and it is rolling out in Flow, Google Vids, the Gemini app (for AI Ultra subscribers) and Google Ads.