← Blog

AI tools2026-11-06Source blog.google

What is Gemini Omni 1.2 Flash? Google's new video model

Gemini Omni 1.2 Flash is Google DeepMind's video generation and editing model, generally available on November 5, 2026, with native clips up to fifteen seconds.

Google DeepMind launched Gemini Omni 1.2 Flash on November 5, 2026 and made it generally available on the Gemini API and Google Cloud. The release extends native video length to fifteen seconds, with one-second steps from three to fifteen seconds, so a single generation can cover product explainers, social ads, or short stories.

Pricing for 720p video is listed at 0.07 US dollars per second, about thirty percent lower than Gemini Omni 1.1. The recommended workflow is to draft at 360p or 720p, refine details in follow-up turns instead of regenerating the whole clip, then upscale the best takes to 1080p or 4K.

Reference adherence is stronger. You can combine character, product, or style images, motion clips up to three seconds, and audio cues, and the model keeps faces, garments, packaging typography, and brand colors consistent across camera moves. Multi-turn conversational editing works on full fifteen-second clips, so you can swap a product, background, lighting, or aspect ratio without starting over.

Speech and camera control also improve. Google describes more natural dialogue, clearer lip sync, and distinct multi-speaker conditioning, plus steadier cinematic moves such as FPV flythroughs and orbits with fewer unwanted cuts. Outputs carry an imperceptible SynthID watermark. In Google Vids, people with a Google account or Workspace subscription can generate a limited number of fifteen-second clips each month at no extra charge.