Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips

Google has released Gemini Omni 1.2 Flash, an updated video generation model announced on November 5, 2026, in a post by Google DeepMind product manager Anish Nangia. The company says the model is generally available through the Gemini API and Gemini for business, marking the first time Omni has reached general availability, with Google Cloud infrastructure and Provisioned Throughput behind it.

The headline change is clip length: native generation and editing now run to 15 seconds, up from 10 in Omni 1.1, with durations selectable in one-second steps from 3 to 15. Google has cut pricing 30 percent from the previous version, to $0.07 per second for 720p video. It suggests drafting at 360p or 720p, fixing details through follow-up edits and then upscaling the best results to 1080p or 4K.

Google also claims tighter adherence to reference images, short motion clips and audio cues, with less visual drift in faces, garments and typography. Other promised gains include multi-turn conversational editing across full clips, more natural multi-speaker dialogue and lip-sync, and steadier continuous camera moves with fewer unwanted jump cuts. Outputs carry an imperceptible SynthID watermark, and Google acknowledges that fast sports action, rapid script changes and complex physics still need work.

The model is rolling out to Flow, Google Ads, Google Vids at no added cost for account holders, and the Gemini app for AI Ultra subscribers. The release matters most for businesses making ads and product videos in volume, where cheaper generation and editing without restarting could lower production costs.