Google DeepMind's Genie 4 adds real-time audio, longer scenes

Genie 4 arrives a couple of months after AI video startup Runway released its second world model, GWM Worlds 2, a playable model with audio generation. Google's release also comes as the world model industry begins to consolidate: Fei-Fei Li's World Labs is being acquired by AMD, Amazon is in talks to buy Decart, and Rivian just acquired Third Dimension to bring simulation capabilities in-house for self-driving testing. Against that backdrop, Genie 4 is Google's latest move to stay ahead in the crowded field, following Genie 3's research preview a little over a year ago.

Within Google's own stack, Gemini is more closely integrated with Genie 4, acting as the director that plans steps and checks frames while Genie creates the visuals. In a research experiment tied to Gemini Robotics, a Gemini 4 Argon model broke down tasks into steps that Genie 4 simulated in real time — showing a possible way to test robot scenarios in simulation before they happen in the real world. Research director Tejas Kulkarni said he expects to see more "hybrid world models" combining Gemini writing code and text with Genie simulating reality in real time.

Beyond the pitched commercial uses of gaming, interactive learning, and robotics, trusted testers are pointing to prototyping films as a possible new use. Google DeepMind engineer Diego Rivas said the real-time aspect is most valuable in the ideation and storyboarding phases, where keeping a state of flow matters. He added that users could eventually rely on Gemini Omni to turn prototypes into creative assets, though those capabilities are still a ways off — and he stressed it's still early days for Genie 4, with the end-to-end product experience not yet clear.