Google unveils Genie 4 world model with audio and real-time steering
Research preview for trusted testers, with rollout to AI Ultra subscribers planned in the coming weeks.
2 minutesMaximum consistent scene length, double Genie 3
The short version
- Google DeepMind released Genie 4 in research preview, available now to trusted testers.
- The model adds native audio and free-form edits, such as changing the weather or camera angle, and can keep a consistent scene for up to two minutes.
- Gemini acts as a guiding agent that plans steps and checks frames while Genie creates the visuals.
- Google says gaps remain: details and objects can drift in longer simulations, and audio accuracy and legible in-world text are still unresolved.
Why it matters
Google describes world models as a key element on the path to AGI. Proposed uses include training environments for robots, testing robot scenarios before they happen in the real world, and rapid prototyping for storyboarding. Developers will get access through the Gemini API and Google AI Studio, but pricing is not yet available.
“What we’ll increasingly see in the future are these hybrid world models”
What people are saying
Hacker News commenters were skeptical about player control, with one saying Genie 4 does not seem to respond to inputs. Others praised the painting-to-interactive-scene demo but noted physics errors in a marble bust clip. One commenter suggested world models could become a new form of cloud-streamed game DRM.