88Z AI, 19 November — Google DeepMind has launched Genie 4 for Google AI Ultra subscribers, marking its most realistic world model to date. The system generates interactive 3D worlds featuring native audio, allows real-time modification via text prompts, and introduces a community gallery for sharing and remixing creations.
At a glance
- Genie 4 is DeepMind's most realistic world model yet, featuring native audio and interactive 3D generation
- Users can edit worlds in real time via text and share or remix creations through a new community gallery

Core Upgrade: Genie 4 Delivers Realistic Interaction and Native Audio
Google DeepMind has officially released Genie 4 to Google AI Ultra subscribers, labeling it as the company's most realistic world model to date. A significant advancement in this version is the first-time integration of native audio generation, creating more immersive and complete interactive 3D environments with both visual and auditory fidelity.
Creative Innovation: Real-Time Text Editing and Community Sharing
Beyond sensory improvements, Genie 4 enables users to modify generated 3D worlds in real time using text inputs, significantly lowering the barrier to content creation. Additionally, DeepMind has introduced a new community gallery feature, allowing users to showcase their creations and remix others' work, fostering collaboration and iteration within the generative AI ecosystem.
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.
- the-decoder.comSource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.