Build Your Next Story with Gemini Omni.

Why It Matters

Omni could accelerate content creation and post-production workflows by making high-fidelity video generation and natural-language editing widely accessible, raising both productivity and content quality while intensifying debates on synthetic media governance. This rollout positions Google to compete strongly in the growing market for multimodal AI tools across enterprise and creator ecosystems.

Summary

Google announced Gemini Omni, a new multimodal generative model that combines Gemini’s reasoning with advanced media models to create and edit highly realistic videos, images and simulations from any input. Omni advances intuitive physics and world understanding, enabling more accurate simulations of kinetic energy, gravity and complex processes like protein folding. It supports iterative, conversational editing of user-supplied footage—transforming selfies or scenes and updating the whole context to match edits. The company launched the first family member, Gemini Omni Flash, now rolling out across its products, with a pro version promised later.