Explore Google Gemini Omni AI video generator with chat-based editing, synced audio, key features, benefits, limitations, and how to use it.

Google's Gemini Omni is a new multimodal model that reasons across text, images, audio, and video to generate and edit videos through simple conversation — starting with Omni Flash.

Google just announced Gemini Omni, a new AI model that it claims can “create anything from any input,” at its annual I/O developer conference on Tuesday. The company said the model is starting off with just video generation and editing capabilities.

Google I/O 2026 unveiled Gemini Omni, Gemini 3.5 Flash, Gemini Spark and a reimagined Search, reframing its products around AI agents that act on a user's behalf.

Google Introduces Gemini Omni, a Multimodal AI That Knows the World

The model marks Google's bid to collapse the multimodal generative stack — text-to-image, image-to-video, video-to-video, audio generation — into a single foundation model with a single editing surface.

Google just announced major updates for the Gemini app, including a new design language, powerful AI agents, and more.

Gemini Omni doesn't just create AI video, it remembers your edits, understands physics, and lets you direct the whole thing through plain conversation. Here's what it actually does and who can use it today.

Google just unveiled a brand new AI world model at Google I/O 2026 called Gemini Omni. While Google calls Gemini Omni a "new model that can create anything from any output," its showcase focused on the AI model's video-generation capabilities.

Google introduced Gemini Omni, a new AI video model that can create and edit cinematic clips using text, images, audio, and video inputs with realistic physics

Google I/O 2026 was all about AI. From advanced AI features in Search to updated Gemini models, here's everything that was announced at the event.