# Google Unveils Next-Gen World Model Genie 4

- Category: Flash (快讯)
- Published: 2026-10-28T12:00:00.000Z
- Source date: 2026-10-28
- HTML: https://www.88z.ai/en/news/flash-20261028-afd160ffffa1c032
- Markdown: https://www.88z.ai/en/news/flash-20261028-afd160ffffa1c032.md
- Other language: https://www.88z.ai/news/flash-20261028-afd160ffffa1c032.md

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

- [量子位](https://mp.weixin.qq.com/s/GAKV3a_ry4o2VAjf7XF1Ew) (2026-10-28)

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.