Genie 4 - Turn a prompt into a living world you can steer
by•
Genie 4 is Google DeepMind’s new real-time world model for creators, game developers and AI researchers. Unlike video generators that hand you a finished clip, Genie 4 builds a world you walk through with your keyboard and steer with text as it runs: change the weather, add a character, set an event in motion. It generates native audio and live dialogue, simulates physics and natural human motion, and uses Gemini to keep scenes coherent. Research preview, waitlist open now.
Replies
Hi PH! Meet Genie 4 is a new world model, which unlocks unprecedented realism and improves real-time interactive simulation. Genie 4 is natively multimodal, enabling audio-like music, ambient noises, and interactive dialogue to be simultaneously generated with the world. Check out the video, this is the one where I turned the sound on and actually said “wait, what” out loud!
Genie 4 doesn’t make a video. It makes a world you walk around in, and you can change it while you’re in it. Type “make it rain” and it rains. Add a person and they talk back.
The physics jump from Genie 3 is real. So is the audio, which they generate natively rather than adding later.
It’s a research preview, so expect some drift in long sessions. Still, filmmakers and game devs, this one’s for you.
Check out the details here https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/
Hi! Cay, you start from your own image, like a photo of a real place, and walk into it?
Congrats on the launch! Not a game dev, but even as just a person who likes games, this looks incredible