DeepMind announces Genie 4 real-time world model with native audio
Original title: Genie 4: A new generation of world simulation
A research preview goes to trusted testers first, then Google AI Ultra subscribers in Project Genie and early Gemini API partners.
Google DeepMind announced Genie 4, a natively multimodal world model that generates interactive simulations together with ambient sound and dialogue. Gemini Omni anchors appearance and behavior, while Gemini 3.8 Flash watches frames, breaks goals into steps, and adapts when the user intervenes. DeepMind is also testing Gemini 4 Argon with Genie 4 on robotics tasks, including a simulated Apptronik Apollo humanoid. The model remains an early research preview before a wider consumer and developer rollout.
- Keyboard controls and text prompts can change weather, camera, people, or objects in real time.
- Genie 4 is DeepMind's first real-time world model that generates audio natively.
- A Project Genie waitlist is open ahead of Google AI Ultra access.
- Vendors
- Google DeepMind
From the original article
8 min read at deepmind.google
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
By Raia Hadsell, Diego Rivas and Hang Qi · deepmind.google
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.