Google DeepMind announces Genie 4, a world model with built-in sound and real-time steering
Google DeepMind announced Genie 4, a world model that generates interactive, real-time simulations with native audio and lets people change the scene with text prompts, now in a research preview for trusted testers.
What happened
- On October 27, 2026, Google DeepMind announced Genie 4, its new world model for real-time interactive simulation.
- DeepMind says Genie 4 generates audio such as music, ambient sound and dialogue together with the world, and builds on Gemini models, including Gemini Omni, to keep simulations realistic and coherent.
- Users move through a world with keyboard controls and can change it mid-session with text, such as changing the weather, moving the camera or adding a person or object.
- It is rolling out as a research preview for trusted testers first. DeepMind says consumer and developer access will start with Google AI Ultra subscribers in Project Genie and early access partners of the Gemini API and Google AI Studio, and a waitlist is open.
- DeepMind lists limits: details and object permanence can drift in longer sessions, and complex physics, text rendering and long-term consistency are still being worked on.
Why it matters: Interactive world models are moving from demos toward products that game makers, agent developers and robotics teams can build on. Genie 4 is not broadly available yet, so watch for Gemini API access.
Sources
- Google DeepMind: Genie 4, a new generation of world simulation deepmind.google
Checked October 28, 2026 against the sources above. Claims about performance or benchmarks are the company's own unless stated otherwise.