Google introduces Gemini Omni, a unified any-input-to-video model
Gemini Omni Flash rolled out free inside YouTube Shorts Remix, letting users restyle or insert themselves into existing videos, with every output carrying a SynthID watermark.
- Models & capabilities
- Notable
Google introduced Gemini Omni at its I/O 2026 developer conference, describing it as a model that can “create anything from any input” — combining text, image, audio and video in a single prompt and generating output grounded in Gemini’s underlying world knowledge, with video as its starting focus. A faster variant, Gemini Omni Flash, launched at the same time and was made available free of charge inside YouTube Shorts Remix and the YouTube Create app for users aged 18 and over.
Through Shorts Remix, a user could take an eligible existing Short, add a text prompt or an image, and have Omni Flash restyle the scene or insert the user into it while preserving the original clip’s context; the original creator’s video remained linked as the source. Every video the system produced, including remixes, carried Google’s SynthID digital watermark, which the company said could be verified through the Gemini app, Gemini in Chrome, and Search — a provenance measure aimed at the growing volume of AI-edited video circulating on the platform.
The release paired capability with reach: rather than launching as a standalone product, Omni Flash shipped directly inside one of the world’s largest short-video platforms, alongside Gemini 3.5 Flash, the agentic and coding-focused model Google unveiled the same day.