Gemini Omni Flash update brings 15-second AI videos and a 30 percent price cut
Google released Gemini Omni 1.2 Flash on Thursday, November 5, extending its AI video model to 15-second clips and cutting the price by 30 percent. It's also the first version of Gemini Omni that Google offers as generally available, which means businesses can now build products on it with Google Cloud's production backing.
What changes in version 1.2
The biggest change is length. Omni 1.2 Flash generates and edits videos up to 15 seconds long, up from 10 seconds with Omni 1.1. You can set the duration anywhere from 3 to 15 seconds in one-second steps.
Editing now works as a conversation. Instead of generating a clip again from scratch, you can ask for follow-up changes to the same video, such as swapping a product or background, changing the lighting or switching the aspect ratio.
Google says the model sticks more closely to the material you give it. You can guide a clip with character, product or style images, motion clips of up to 3 seconds and audio cues. The company claims faces, clothing, packaging text and brand colors now stay consistent across camera angles, with less drift and morphing from the first frame to the last. Google Cloud says audio references are limited to allowlisted customers.
Google also says dialogue sounds more natural, with clearer lip-sync and better handling of several speakers, and that camera moves such as drone-style flythroughs have fewer unwanted jump cuts. It admits the model still needs work on fast sports action, rapid script changes and complex physics.
Price and availability
A second of 720p video now costs $0.07, which Google says is 30 percent less than Omni 1.1. At that rate, a full 15-second clip at 720p costs $1.05. Google suggests drafting at 360p or 720p, fixing details with follow-up edits and then upscaling the best results to 1080p or 4K.
The model is generally available on the Gemini API and Google Cloud, where Google offers Provisioned Throughput. Every output carries an imperceptible SynthID watermark, according to Google.
Outside the developer tools, Google is rolling the model out to:
- Google Vids: 15-second clips at no additional cost with a Google account or Google Workspace subscription.
- Gemini app: 15-second videos, rolling out to Google AI Ultra subscribers.
- Flow: scene direction and multi-turn edits.
- Google Ads: video campaigns for advertisers.
What it means for you
If you have a Google account, you can try the model in Google Vids and make 15-second clips there at no additional cost. In the Gemini app, it's rolling out to Google AI Ultra subscribers.
On the developer side, Google Cloud says the model is built for the videos businesses make in volume, such as product videos, virtual try-ons and ads. Google says 15 seconds is enough for a full social ad in a single generation.