Google just announced Genie 4: Here’s what it can do, from building walk-through worlds out of a sentence to filling them with sound and speech, and when you might get to try it

Google DeepMind has announced Genie 4, its AI world model that turns a text prompt or photo into an interactive world you can explore in real time. Genie 4 adds lifelike people, realistic physics, native sound and talking characters, and lets users change scenes on the fly. Here’s how Genie 4 works, its limits and when it reaches Google AI Ultra subscribers via Project Genie.