On November 5, 2026, Google DeepMind introduced Gemini Omni 1.2 Flash, a video generation and editing model.
What to know
- Length: Google says clips can now run up to 15 seconds, up from 10 seconds in Omni 1.1, with duration selectable in one-second steps from 3 to 15.
- Price: Google lists $0.07 per second for 720p video and says this is 30% lower than Gemini Omni 1.1. It suggests drafting at 360p or 720p, then upscaling to 1080p or 4K.
- References: Google says you can guide it with character, product or style images, motion clips of up to three seconds, and audio cues.
- Other changes Google lists: multi-turn conversational editing, better consistency across frames and shots, more natural speech with lip-sync and multiple speakers, and more controllable camera movement with fewer jump cuts.
- Where: generally available in the Gemini API (model ID
gemini-omni-1.2-flash) and Google Cloud. Google says the Gemini app rollout to Google AI Ultra subscribers is under way, and it is also in Flow and Google Ads. - Google Vids: in a separate post, Google says anyone with a Google account or Workspace subscription can make up to three 15-second videos a month at no cost, starting November 5.
- Limits Google names: fast sports action, rapid script changes and complex physics are still in development. Outputs carry a SynthID watermark.
Why it matters
Longer single-take clips make product promos and social posts easier without stitching shots. Try our own prompts in how to prompt Gemini Omni 1.2 Flash. See also Veo, the Gemini page and the model tracker.
Source: Google. We summarise in our own words; check the source for the full details.