Google’s Gemini Omni 1.2 Flash makes 15-second AI videos and cuts the price by 30%

Google on November 5 rolled out Gemini Omni 1.2 Flash, an update to its video generation model that makes longer clips, follows reference material more closely and costs less to run. The model is now generally available through the Gemini API and Gemini for business, and it is also coming to Google’s consumer apps.

What changed

• Longer clips. Videos can now run up to 15 seconds natively, up from 10 seconds with Omni 1.1. Length can be set in one-second steps from 3 to 15 seconds.
• Lower price. According to Google, the price is 30% lower than Omni 1.1, at $0.07 per second of 720p video. At that rate a full 15-second 720p clip works out to $1.05.
• Editing in conversation. Users can change a finished clip turn by turn, for example swapping a product or background, changing the lighting or weather, or switching the aspect ratio, instead of generating it again from scratch.
• Better use of references. Prompts can combine character, product or style images, short motion clips of up to three seconds and audio cues. Google says faces, clothing, packaging text and brand colours now stay more consistent from the first frame to the last.

Google also suggests a cheaper workflow: draft at 360p or 720p, fix details with follow-up edits, then upscale the best result to 1080p or 4K.

Where you can use it

Developers can try the model in Google AI Studio and businesses in the Google Cloud console, where Provisioned Throughput is available. On the consumer side, Omni 1.2 Flash is coming to Flow, to Google Ads, and to the Gemini app, where 15-second videos are rolling out to Google AI Ultra subscribers.

The most accessible option is Google Vids. In a separate post, Google says anyone with a Google account or a Google Workspace subscription can now make up to three 15-second videos a month in Vids at no cost.

Ten seconds was often too short for a complete ad or product explainer, so the jump to 15 seconds, together with the price cut, is aimed squarely at businesses that make video at scale. Every output carries Google’s invisible SynthID watermark, which helps identify AI-generated footage.

Google is also open about the limits: it says work is still ongoing on fast sports action, rapid script changes and complex physics.

Reported by Google, Google Workspace. Compiled with AI tools.