Google DeepMind launches Genie 4 for interactive 3D worlds to AI Ultra subscribers
Genie 4 adds real‑time text editing, native audio and a community gallery, while Genie 3 gains longer sessions and panorama support.
Google DeepMind announced that Genie 4, its newest world‑generation model, is now available to Google AI Ultra subscribers.
Genie 4 lets users reshape environments on the fly with text prompts, adding weather changes, characters or story elements, and it produces adaptive native audio.
The update also includes a new Project Genie agent that builds worlds from spoken or conversational descriptions and a community gallery for sharing and remixing creations.
Genie 3 receives upgrades: sessions can last up to three minutes, it supports 360‑degree panorama grounding, and worlds can be chained together for longer journeys.
What it means for you
For creators, Genie 4 offers more control and instant feedback when building immersive 3D experiences. While these tools are tied to Google’s subscription tiers, the free‑model rankings on FreeLLMArena show strong alternatives for chat‑based AI, with Kimi K3 and GLM‑5.3 leading the free segment.
Sources
- Google Deepmind's Project Genie update brings Genie 4, chainable worlds, and a community gallery for remixing, The Decoder, 18 Nov 2026
- Project Genie update featuring Genie 4, blog.google (official), 18 Nov 2026
Written automatically from the sources above, then checked by our code: every number and name must appear in them, and no sentence may copy a source. Spotted a mistake? Report it.
Which AI can you use for free today?
Every free AI model, ranked by blind human votes, with the memory and speed it needs on your own GPU.