What Google announced
On November 5, 2026 Google introduced Gemini Omni 1.2 Flash, its video generation and editing model, and made it generally available on the Gemini API and Google Cloud. In Google's words: "We are launching Gemini Omni 1.2 Flash with support for fifteen-second videos and improved reference adherence." The post is by Anish Nangia, Product Manager at Google DeepMind.
What is new
Clips can now be up to 15 seconds long, up from 10 seconds with Omni 1.1, and you can set the length in one-second steps from 3 to 15 seconds. You can also edit a clip through several conversational turns, for example swapping a background or changing the aspect ratio, instead of starting over. One generation tops out at 15 seconds; Google's documentation says clips can be extended by 3 to 10 seconds per turn, up to 30 seconds in total.
Google says the model follows character, product and style references more closely, keeps scenes more consistent from the first to the last frame, and produces more natural dialogue and lip-sync. These are Google's claims, illustrated with Google's own example clips; Google adds that work continues on fast sports action, rapid script changes and complex physics. The announcement also mentions audio cues as inputs; in the current Gemini API, Google's documentation says uploading audio inputs or audio references is unsupported and voice editing is not supported. Native audio output works.
Price and availability
Google says it "dropped the price 30% from Gemini Omni 1.1 making it available at $0.07 per second for 720p video." The Gemini API pricing page adds per-second estimates for other resolutions: about $0.023 at 360p, and about $0.104 at 1080p and $0.209 at 4K with upsampling. We took those figures from the pricing page on November 7, 2026; the announcement itself gives only the 720p price. These figures cover video output only; input tokens cost $1.50 per million and text output $9 per million on top, and there is no free API tier.
Outside the API, Google lists Flow, 15-second clips in Google Vids at no additional cost, 15-second videos in the Gemini app (rolling out to Google AI Ultra subscribers) and Google Ads. Outputs carry an imperceptible SynthID watermark. In the EEA (including Poland), Switzerland and the UK, the API does not support editing or extending uploaded videos; model-generated videos can be edited or extended, and uploading or editing images containing minors is unsupported there. Availability of each consumer surface still needs checking in your account.
What it means for you
If you make short ads, product spins or explainers, a full 15-second spot now fits in one generation, and conversational edits can make variants cheaper than regenerating. Draft at 720p, check consistency and audio, and upsample only the take you keep. If you use the API with gemini-omni-1.1-flash, Google's pricing page says requests will be routed to 1.2 Flash and billed at its rates from December 3, 2026.
Go to the source
Sources & further reading
Based on the official documentation below. Features and access can change; check the provider before making a decision.
Was this page useful?
Help us make our coverage more useful. This is feedback on the page, not a rating of the tool.
Go a little further