Google DeepMind's Genie 4 builds interactive worlds that make their own sound
Google DeepMind's Genie 4 is a natively multimodal world model that generates photorealistic, real-time interactive simulations complete with music, ambient noise, and spoken dialogue. Built on Gemini, it lets users reshape scenes in natural language while Gemini keeps the world coherent between inputs. It's rolling out as a research preview to trusted testers, starting with Google AI Ultra subscribers in Project Genie and early Gemini API partners.
With this foundation, you can set an event in motion, and Genie 4 simulates what happens next: how the world responds, how it sounds, and how the people in it move, react, and speak.