Google’s Gemini Omni turns images, audio, and text into video — and that’s just the start

Google has unveiled Gemini Omni, a new family of multimodal AI models capable of reasoning across text, audio, images, and video to generate high-quality video output. By synthesizing these diverse inputs, the model aims to simulate reality with an understanding of physics and context. Currently available as Gemini Omni Flash, the tool allows consumers to create personalized content, such as digital avatars and creative videos, while incorporating SynthID watermarking for safety and accountability. Future iterations, including a more powerful Pro version, are expected to expand utility for professional filmmakers and advertisers.

(Source：TechCrunch)