Scoop
AI tool news · rumor vs. reality

The AI Wire ●

Rumors tracked. Announcements verified. Updated daily.

RELEASED

Google opens Genie 4 to AI Ultra subscribers in Project Genie: worlds you can redirect mid-session, now with native audio

Google rolled out a new Project Genie experience to eligible Google AI Ultra subscribers on November 18, opening first-time access to Genie 4, its most realistic and interactive world model. Google AI Pro members can join a waitlist on the Project Genie page; the rollout follows Genie 4's October 27 research preview for trusted testers, covered by the Wire at the time.

Genie 4 lets users prompt mid-session to change the world they are inside — shifting the weather, adding a character or object, moving the camera or redirecting events without starting over. For the first time, Genie pairs its visuals with real-time native audio that adapts as the scene unfolds, from ambient soundscapes to character dialogue.

The new experience also adds the Project Genie agent, which helps users build their vision, and a community gallery for discovering, exploring and remixing other people's worlds. Genie 3 remains available and received upgrades of its own, including longer runs.

Google is explicit that Genie 3 and Genie 4 remain frontier research systems. It names camera latency, intricate physical interactions, real-time audio precision and long-term scene permanence as unresolved challenges, and all generated video and audio carries SynthID watermarking and passes safety screening.

Update, November 19: Genie 4 is now also available to developers through the Gemini API, via the Interactions API, and in Google AI Studio. Developers can start from a text prompt, a reference image or both to generate continuous 720p worlds at 24fps with synchronized native audio, navigate with real-time keyboard controls alongside live text prompts, and change weather, lighting, objects or events on the fly, with Gemini reasoning keeping the world state consistent. Google pitches it for prototyping interactive experiences, visualizing spatial designs and training robotics and AI agents; every output carries SynthID watermarking.

Sources

← Back to headlines