Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering
Summary
Google DeepMind has launched a research preview of Genie 4, its latest world model capable of generating highly photorealistic and interactive environments. Unlike its predecessor, Genie 4 supports real-time audio generation—including music and ambient noise—and allows users to steer simulations through text prompts to change weather, camera angles, or objects mid-simulation. The model can maintain scene consistency for up to two minutes and features improved physics and more human-like characters.
Genie 4 is deeply integrated with Google's Gemini models, which act as a
(Source:TechCrunch)