Google released Gemini Omni 1.2 Flash on November 5, an update to the video model it made generally available in August (our earlier report). The headline changes are longer clips, a lower price and editing that no longer means starting over.
What changed
15-second clips. Videos can now run up to 15 seconds, up from 10 in Omni 1.1, with the length set in one-second steps from 3 to 15 seconds. Drafts are generated at 360p or 720p and can be upscaled to 1080p or 4K.
Lower price. In the Gemini API, 720p video costs $0.07 per second, 30% less than Omni 1.1.
Edits without regenerating. Multi-turn editing lets you swap a product or background, change lighting or weather, or switch the aspect ratio with a follow-up request, instead of generating the whole clip again. Google says characters, products and brand colors stay more consistent from the first frame to the last, and speech and lip-sync are clearer. Every clip carries an invisible SynthID watermark.
Where it is available
The model is generally available in the Gemini API, Google AI Studio and Google Cloud. In the Gemini app, 15-second videos are rolling out to Google AI Ultra subscribers. Google Vids offers 15-second clips at no additional cost to users with a Google account or Workspace subscription, and the model also powers Flow and video campaigns in Google Ads.
What this means if you make video with AI
Check where you would use it. In the Gemini app the new length is limited to the top AI Ultra plan for now, while Google Vids gives it to ordinary accounts. Google itself notes the model still struggles with fast sports action and complex physics.
Editing is the practical gain. Fixing one detail with a follow-up request saves the generations you would otherwise spend re-rolling a clip. To compare video generators, see the list of AI video tools and our guide to AI for video generation.