Genie 4: Google DeepMind's real-time world model with native audio
Google DeepMind announced Genie 4 on Tuesday, a world model that generates interactive simulations in real time, steered with natural language and with native audio. It is a research preview for a limited group of trusted testers; Google says it is coming soon to Google AI Ultra subscribers in Project Genie and to early access partners in the Gemini API and AI Studio, with no date in its posts.
What it means for youthe waitlist is open in Project Genie, and long sessions may still drift.
With Jonah, AI products analyst. Hosted by Vivian.
Sources
- Google: We're announcing Genie 4, our new world model for real-time interactive simulation blog.google, Oct 27, 2026
- Google DeepMind: Genie 4, a new generation of world simulation deepmind.google, Oct 27, 2026
Read the transcript
VivianGoogle AI Ultra subscriber? Genie 4, Google DeepMind's real-time world model with sound, is coming soon to Project Genie.
VivianJonah, our AI products analyst. What does it do, and who can use it?
JonahYou steer a live scene with plain language: move the camera, change the weather, add characters. Each world makes its own sound, from music to dialogue. Right now it's a research preview for trusted testers. Ultra subscribers and early access partners in the Gemini API are next, and Google's post gives no date. There's a waitlist.
VivianOne question we checked: how long does a world stay consistent, say when you turn around?
JonahDeepMind says it holds together over short sessions, but details and object permanence can still drift over time. Its blog doesn't give a length.
VivianSo, for you: the waitlist is open in Project Genie, and long sessions may still drift.
VivianDailyChat is AI-generated, with AI characters. Not professional advice. See you tomorrow.