What Gemini Omni 1.2 Flash Is and What It Can Do

What is Gemini Omni 1.2 Flash?

Gemini Omni 1.2 Flash is a Google model for generating and editing video. It is designed for tasks such as making product videos, virtual try-ons, and ads. Google describes it as fast and cost-effective for producing videos in volume. ¹²

It is a model, not a separate general-purpose chatbot described in the supplied announcements. Google says people can use it through the Gemini API, Gemini for business, and Google Vids. Developers can also build it into other products through the API. ¹²

What can it make and edit?

The model can create video clips up to 15 seconds long. Google says users can choose a duration in one-second steps from 3 to 15 seconds. That is longer than the 10-second maximum cited for the previous version, Gemini Omni 1.1. ¹

It also supports conversational editing: a user can request a change in a follow-up instruction rather than generating the whole clip again. Google says this can help users adjust a detail and keep the workflow efficient. The announcement does not give a complete list of supported edits or explain how reliably each kind of request works. ¹

How does it use image, video, and audio references?

A reference is material that a user provides to guide the result. Google says Gemini Omni 1.2 Flash follows image, video, and audio references more closely than before. This may help a creator guide the look or content of a generated video, though the supplied announcements do not spell out every reference type or its limits. ²

Google also highlights improved consistency and reference following. These are claims from the company, not independent test results in the research provided here. Readers should not assume every output will match a reference exactly. ¹²

Where can people use it, and what does it cost?

Google says the model is generally available through the Gemini API and Gemini for business, and can also be used in Google Vids. Availability in other creative platforms may depend on those companies’ products and plans. ¹²

Google lists the price for 720p video at $0.07 per second, a 30% reduction from Gemini Omni 1.1. The company says users can draft at 360p or 720p, make follow-up edits, and upscale selected videos to 1080p or 4K. The provided sources do not explain all possible costs, account requirements, or regional availability, so check Google’s current product information before relying on a price. ¹

What should users know about safety and reliability?

Google says generated outputs carry an imperceptible SynthID watermark. A watermark is information added to content to help identify its origin; the company’s announcement describes this one as not visible to the eye. The sources do not explain how users can check a particular video for the watermark. ²

Google describes the service as production-ready and says it is backed by Google Cloud infrastructure and security. Those are company statements. The supplied research does not include independent security reviews, detailed privacy terms, or tests of how the model handles mistakes, so users should consult the applicable Google product documentation for those details. ²