AI BriefingGoogle Testing New Omni Video Generation Model
Key point
Signs have emerged that Google is testing a new Omni model in the Gemini video generation tab.
Details
A screen showing the phrase Powered by Omni was discovered in Gemini's video generation tab, revealing that Google is testing a new Omni model. The phrase appears near the existing Toucan label, raising the possibility of a connection to the current Veo-based flow.
Right now, Gemini's video generation is handled by Veo 3.1, while images are handled by Nano Banana 2 and Nano Banana Pro. Google describes Nano Banana Pro as based on Gemini 3, and Nano Banana 2 as Gemini 3.1 Flash Image.
The identity of Omni remains open.
- A new wrapper for Veo
- A separate Gemini video model
- An early omni-model that handles both images and video together
Since it was directly exposed in a UI string, it may also be a public product name. Amid the AI video competition where ByteDance Seedance 2.0 currently leads, Google may use Google I/O 2026 (May 19-20) as a bigger stage to unveil Gemini media generation.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.