Google DeepMind introduces Genie 4, a real-time interactive world model

Google DeepMind announced Genie 4 on October 27, 2026, calling it its most realistic and interactive world model yet. In its post, DeepMind says users can explore dynamic environments in real time and see how the scene responds, sounds, and how the people in it move, react and speak. It published a blog post, "Genie 4: a new generation of world simulation".

DeepMind's blog post says Genie 4 is natively multimodal, generating ambient sound, music and interactive dialogue with the world, and that it builds on the Gemini family: Gemini 3.8 Flash acts as a guiding agent that watches the scene, breaks goals into steps and adapts the plan as the user intervenes. DeepMind calls it an early, experimental model. It is rolling out as a research preview for trusted testers, with consumers and developers to follow, starting with Google AI Ultra subscribers in Project Genie and early-access partners of the Gemini API and Google AI Studio.

Accounts on X relaying the announcement say it is on a waitlist and rolling out to Google AI Ultra users, with native audio including dialogue, real-time prompt controls, and Gemini reasoning for longer coherence. These details are the relays' reading, not DeepMind's post.