88Z AI, 28 October — Google DeepMind has released Genie 4, a model that generates interactive virtual worlds from text, featuring real-time physics simulation and native audio generation for synchronized sound effects and character dialogue.
At a glance
- Genie 4 generates modifiable virtual worlds with physics from text
- Supports native audio generation for real-time synchronization of sounds and dialogue
The update
Google DeepMind has officially launched Genie 4, its next-generation world model. This system allows users to generate explorable virtual worlds using simple text prompts, enabling on-the-fly adjustments to weather, characters, and scenes while simulating realistic physics. As Google's first real-time world model with native audio generation, Genie 4 marks a breakthrough in audiovisual experience. It synchronously produces environmental sounds and music, while allowing virtual characters to engage in real-time dialogue based on the context, significantly enhancing the immersion and realism of the virtual environment.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 量子位Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.