Google DeepMind announces Genie 4 for real-time world simulation with native audio

What happened

Google DeepMind has released Genie 4 as a research preview for trusted testers, adding native audio, interactive dialogue, and real-time natural-language steering to world simulation. Gemini 3.8 Flash guides multi-step events by observing scenes, planning actions, and checking progress. Access is coming soon to Google AI Ultra subscribers in Project Genie and early access partners in the Gemini API and Google AI Studio; object permanence, physical interactions, and long-term consistency remain research challenges.

Read next

• More changes in today’s briefingIntroducing GPT-6.1 Terra

Reported by 7 sources

The story so far

Google DeepMind has released Genie 4, its model for generating interactive virtual worlds, as a research preview for trusted testers. Google says access is coming soon to Google AI Ultra subscribers through Project Genie and early access partners through the Gemini API and Google AI Studio; TechCrunch reports that rollout is planned in the coming weeks. Google has also opened a waitlist to try it in Project Genie. DeepMind says Genie 4 adds native audio and conversational characters, with natural-language controls for changing environments and soundscapes during simulations, including adjusting weather, moving the camera and adding elements. It says Gemini 3.8 Flash guides multi-step events by observing scenes, planning actions and checking progress. The Verge reports that experiences can last about two minutes, up from one minute with Genie 3, though scene details and object consistency can shift over time. TechCrunch also identifies audio accuracy and text legibility as remaining challenges. DeepMind says object permanence, physical interactions and long-term consistency remain research problems.