Google Unveils Gemini Omni—A Next-Gen AI Video Builder That Can 'Simulate the World'
Google announced Gemini Omni, a new multimodal AI model that merges Gemini’s intelligence with advanced generative media tools like Veo, Nano Banana, and Genie. Revealed at Google I/O 2026, Gemini Omni is designed to create diverse media—including video, images, and music—from various input types, representing a significant step toward artificial general intelligence. The first release, Gemini Omni Flash, will launch on Google’s Flow platforms for AI video and music creation. Omni leverages Gemini’s reasoning to follow high-level instructions and can maintain consistency in characters, backgrounds, and movement when editing video, a challenge for existing AI models. Demonstrations included claymation-style educational videos and dynamic, conversational video edits. Google also introduced Flow Agent, an assistant that supports brainstorming and batch editing, and Flow Tools for creating editing workflows via natural language. Omni builds on the popularity and core features of Nano Banana and aims for a broader, flexible creative capability, with plans to expand beyond video generation.
