Google has launched an update to its experimental research prototype, Project Genie, making it available to eligible Google AI Ultra subscribers. This release focuses on providing users with more control over generated worlds, easier creation tools, and improved sharing capabilities.
The update introduces Genie 4, significant upgrades to Genie 3, a new Project Genie agent for building worlds, and a community gallery for discovery and sharing. Project Genie integrates Google's advanced world models with Gemini models to facilitate in-browser world generation and interaction.
Genie 4 is presented as Google's most realistic and interactive world model to date. It allows users to modify their created worlds mid-session by typing new prompts while navigating. This enables real-time changes to environments, such as altering weather, adding characters, or redirecting actions.
A new feature in Genie 4 is the pairing of visuals with real-time native audio. This audio adapts as scenes unfold, incorporating ambient soundscapes and character dialogue.
While Genie 4 offers higher fidelity, Genie 3 remains available for longer runs or panorama-seeded spaces. Updates to Genie 3 include extended session times, now up to 3 minutes per generation, and the ability to link multiple worlds for longer journeys.
Genie 3 also gains 360-degree panorama image grounding, allowing users to seed new worlds from panoramic images. Additionally, it now supports real-time in-world events, enabling dynamic environment changes via natural-language prompts during exploration.
A new Project Genie agent simplifies the creation process, moving beyond single text or image prompts. Users can describe their vision in natural language, and the agent orchestrates Google's multimodal models to generate initial visuals and custom background scores.
The update also allows for the integration of Gemini models into sessions, which observe on-screen activity and surface context-aware information. A community gallery has been added for users to discover, explore, and remix worlds created by others.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Google has released an update to Project Genie for eligible Google AI Ultra subscribers, introducing Genie 4 for real-time interactive world editing and native audio. The update also includes enhancements to Genie 3, such as extended session times and 360-degree panorama grounding, alongside a new Project Genie agent for conversational world creation.