Google introduced Gemini Omni, a multimodal model that generates and edits video from almost any input, at its I/O developer conference on May 19, 2026, moving the company's generative-video effort out of the standalone Veo line and into the core Gemini system. That's not a minor product update. It's an architectural shift in how Google thinks about generative AI.
Until now, Google ran a split stack: Veo for video, Imagen for images, and separate systems for audio. Omni collapses that into one model that can reason across modalities. In practice, that translates to more coherent edits and fewer pipeline artifacts.
Google describes Omni as the point where "Gemini's ability to reason meets the ability to create." That framing is deliberate. This isn't just a video generator bolted onto an LLM. It's a unified system where understanding and generation happen inside the same weights.
What Is Gemini Omni
Gemini Omni is Google DeepMind's first natively multimodal generative media model. The first variant in the family is Gemini Omni Flash, which is now live. Omni accepts any combination of text, images, audio, and video as input and produces a video. The key here is that there's no relay happening across different systems — this is all one model.
Google's AI portfolio now includes Omni, a world model designed to simulate physical environments, predicting what happens next based on a user's actions. That "world model" framing is worth paying attention to. It signals that Google isn't just targeting content creators. It's targeting anyone who needs a system that understands causality, physics, and context well enough to generate believable outputs.
Gemini Omni Flash is the first version to debut, with a Pro model to follow later.
How Gemini Omni Works
The core mechanic is conversational, multi-turn video editing. Users can combine images, audio, video, and text in a single prompt. Rather than stitching those inputs together, the model reasons across them to produce one output and then accepts further changes through conversation.
Every edit you make builds on the one before, maintaining a consistent, coherent scene. Gemini Omni combines an intuitive understanding of physics with Gemini's knowledge of history, science, and cultural context.
Every conversation with the model layers changes and transformations according to the last request. This allows users to change specific details or broader visual elements. The model also takes into account the physics and consequences of requests, allowing users to change the environment, angle, style, and action, as well as add new characters, objects, and details.
