Google DeepMind releases the Genie 4 world model, supporting real-time natural language modification
Google DeepMind has released the Genie 4 world model, positioned as a major research milestone, allowing users to use natural language instructions to change weather, camera, and characters in real time. It is DeepMind's first model to natively generate audio within real-time world simulation, with audio and visuals produced synchronously, and it shows stronger performance in physical scenarios such as aerodynamics and collisions as well as in character movements. Genie 4 is currently available only as a research preview to trusted testers, and in the coming weeks will expand to Project Genie for Google AI Ultra subscribers as well as early partners of the Gemini API and Google AI Studio; engineer Diego Rivas acknowledged that long-duration simulations may show detail drift, and that audio accuracy and the readability of in-frame text have not yet been fully resolved.
Why read this
AI score 80
The original text explains Genie 4's real-time modification, native audio, and physical performance, and also lists drift and readability issues in the early stage.
Topics
Body · AI translation
Real-time "directing" of worlds: Pichai says Genie 4 is Google's most realistic and interactive AI world model to date
English text is being prepared.
English text is being prepared.
For users, the biggest highlight of the Google Genie 4 world model is real-time "directing" of the world. During simulation runs, users can use natural language text instructions to change the world, for example changing the weather, moving the camera, or adding new characters or objects.
Unlike mainstream AI that regenerates a video, Genie 4 executes dynamic changes based on the current scene context, more like an "interactive virtual sandbox" or "AI directing system." Users can set an event and then observe how the world continues to evolve, while intervening and adjusting at any time.
English text is being prepared.
Google CEO Sundar Pichai today posted a tweet on his personal account, saying that Genie 4 is Google's most realistic and interactive world model to date.
In an interview with tech media TechCrunch, Google Research Director Tejas Kulkarni said that in the future Gemini will be responsible for text, code, and task planning, and Genie 4 will convert this content into an interactive world in real time, forming a "hybrid world model."
DeepMind engineer Diego Rivas acknowledged that Genie 4 is still in an early stage; long-duration simulations may show detail drift, and audio accuracy and the readability of text within the frame have not yet been fully resolved.
Genie 4 is currently available only as a research preview to "trusted testers"; in the coming weeks it will expand to Project Genie for Google AI Ultra subscribers, as well as early partners of the Gemini API and Google AI Studio.
Related reading:
"Google launches its most powerful world model Genie 4: create an interactive virtual world with one sentence, achieving synchronized audio-video generation for the first time"