Google opens Genie 4 world model via the Gemini API and AI Studio
11/19/2026 — 11/20, 08:18·6 sources (all)·10 reports (all)
Key takeaways
- Google has opened its Genie 4 world model to developers through the Gemini API and AI Studio, generating 720p, 24fps worlds with native audi…
Background & analysis
In the early hours of 19 November 2026, Google announced through the Google Gemini Blog that it was rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, opening first access to its next-generation world model, Genie 4. Availability was initially limited to that subscription tier. Google DeepMind then confirmed that Genie 4 was live, without disclosing further details on model capabilities, parameters, or access methods. Later that morning, reports filled in the scope of the update: the new experience included Genie 4, new Genie 3 features, a Project Genie agent for building worlds, and a community gallery for sharing and remixing creations. The Decoder and IT之家 reported that Genie 4 generates interactive 3D worlds that can be modified in real time through text input and, for the first time, adds native sound, allowing users to change weather or add characters mid-session. IT之家 also noted that Project Genie integrates the Gemini model family. The Next Web added that Google acknowledged details still drift during long sessions.
From 20 November 2026, Genie 4 reached wider audiences. According to TestingCatalog, Genie 4 became available on Google AI Studio and APIs, letting developers test it directly with an API key, with real-time keyboard controls and live text interaction. The same day, TestingCatalog reported that Google had begun sending Project Genie access notices to waitlisted Gemini Pro users as part of the Google AI Pro subscription, and suggested Genie 4 would eventually reach all Pro users, though the materials contain no formal Google confirmation of this. Later on 20 November, TestingCatalog reported that Google had opened Genie 4 to developers through the Gemini API and AI Studio, streaming 720p worlds at 24fps with native audio, live prompts, and WASD key controls, with the rollout currently stopping at the point where developers can access the model via API and AI Studio.
AI-generated from 10 reports · updated 2 days ago
Latest turnGoogle has opened its Genie 4 world model to developers through the Gemini API and AI Studio, according to TestingCatalog. It streams 720p worlds at 24fps with native audio, and supports live prompts and WASD keyboard controls.
Related AI tools
- Heat index
- 25
- All sources
- 6
- All reports
- 10
- First seen
- 3 days ago
Reports on this story headlines open the original
Google has opened its Genie 4 world model to developers through the Gemini API and AI Studio, according to TestingCatalog. It streams 720p worlds at 24fps with native audio, and supports live prompts and WASD keyboard controls.
TestingCatalogAI score 58Google has begun letting Gemini Pro users off the waitlist for Project Genie, according to TestingCatalog, with notices saying access now comes with the Google AI Pro subscription. The account expects the rollout to eventually reach all Pro subscribers.
X:TestingCatalog (@testingcatalog)AI score 57Google's Genie 4 world model is now available in Google AI Studio and through APIs, according to TestingCatalog. The release gives many developers their first chance to test the model with an API key; it had been limited to Ultra subscribers. The model supports real-time keyboard controls alongside live text interaction.
X:TestingCatalog (@testingcatalog)AI score 64
Google is rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, giving them first access to its Genie 4 world model. Genie 4 lets users edit a generated world mid-session by typing new prompts, switching weather or adding characters, and adds real-time native audio that follows the scene. Project Genie also bundles Gemini models, an agent, and a community gallery.
IT之家AI score 66Google is rolling out Genie 4 to eligible AI Ultra subscribers in Project Genie, its browser-based world-building prototype, alongside a creation agent and a community gallery. The model lets users change worlds mid-session and adds native audio, though Google says details still drift in long sessions.
The Next WebAI score 52Google DeepMind has released Genie 4, which it calls its most realistic world model yet, available to Google AI Ultra subscribers. The update generates interactive 3D worlds that can be edited in real time with text prompts, adds native sound for the first time, and includes a community gallery for sharing and remixing worlds.
The DecoderAI score 67Google is rolling out Genie 4 on Project Genie for AI Ultra subscribers, according to TestingCatalog. The release adds native audio and realtime editing, along with a gallery of pre-made creations that users can explore and remix.
X:TestingCatalog (@testingcatalog)AI score 54Google is rolling out a new Project Genie experience for Google AI Ultra subscribers, featuring Genie 4, new Genie 3 capabilities, a Project Genie agent that builds worlds, and a community gallery for sharing creations. The update is available to that subscription tier.
TechmemeAI score 62Google DeepMind announced that Genie 4 is now available. The announcement did not disclose further details on capabilities, model specifications, or access.
Google DeepMindFirst-partyAI score 58Google is rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, opening access to Genie 4, its new world model. Access is limited to that subscription tier.
Google Gemini BlogFirst-partyAI score 61
Other stories people are talking about
- Heat index 133Google adds GIF generation to Gemini, powered by Omni 1.2 Flash2 sources
- Heat index 66Google opens Gemini Tasks agent mode to free users in six countries1 sources
- Heat index 33Google Rebrands Spark as Tasks, Shifts to Gemini 4 Hydrogen1 sources
- Heat index 64Google Gemini Black Friday: AI Pro annual plan about $99.991 sources
- Heat index 84Google Search and Gemini launch Connected Apps for shopping and tax tasks2 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

