Google DeepMind releases Genie 4, supporting native audio and real-time interaction
BIBIBI
AT A GLANCE
Google DeepMind has announced the launch of world model Genie, supporting native audio and real-time interactive simulations. 4。
Article
Google DeepMind releases world model Genie 4, supporting native audio and real-time interaction
PANews October 28 reports, according to Google's official blog, that Google DeepMind has announced the launch of its next-generation world model Genie 4 for real-time interactive simulations. The model is built on the Gemini family, with Gemini Omni making simulated scenes resemble the appearance and behavior of the real world. While a scene is running, users can use natural language to move the camera, change the weather, or add new characters. Each world also generates native audio in real time, including ambient sounds, music, and interactive dialogue. Genie 4 is currently available to a small group of trusted testers and will subsequently be rolled out to Google AI Ultra subscribers in Project Genie, as well as Gemini API and AI Studio early partners.
PANews reports that Google DeepMind has announced the launch of its next-generation world model Genie 4。
02
Genie 4 for real-time interactive simulations, built on the Gemini family.
03
While a scene is running, users can use natural language to move the camera, change the weather, or add new characters.
04
Each world generates native audio in real time, including ambient sounds, music, and interactive dialogue.
05
Genie 4 It is currently available to a small group of trusted testers.
06
It is subsequently planned to be rolled out to Google AI Ultra subscribers in Project Genie, as well as Gemini API and AI Studio early partners.
AI-assisted interpretation
The following is analysis, separate from reported facts. Verify important claims independently.
Genie 4 It can generate simulation scenes that can be operated in real time. Users can use natural language to change the camera, weather, or characters, while the scenes simultaneously generate ambient sounds, music, and dialogue.
Why it matters to readers
It combines scene generation, real-time natural-language operations, and native audio in a single simulation experience, but availability is currently limited.
Beginners can understand it as a model that can generate and modify virtual scenes in real time; it is currently mainly in limited-scale testing.
Risks and unknowns
Evidence states that the news comes from Google's official blog, but does not provide the original link to that blog.
The specific subsequent availability timeline has not been specified.
The evidence does not provide test results, performance data, or tester feedback.
Related Developments
Loading event timeline…
Related concepts
world model
This term is not in the glossary yet. Browse related concepts in the glossary.
