DeepMind launches Genie 4 for Google AI Ultra subscribers
What happened
Google DeepMind has moved its world model Genie 4 from research preview to availability for eligible Google AI Ultra subscribers in Project Genie; Google AI Pro members can join a waitlist on the same page. Previously, Genie 4 was available only as a research preview to trusted testers, with early partners in the Gemini API and Google AI Studio slated to gain access afterward. In Project Genie, users can enter prompts while exploring to change the weather, add characters, or alter the direction of the story in real time; Genie 4 also pairs for the first time with real-time native audio that changes with the scene. The company says Genie 3 and Genie 4 remain world models at the frontier research stage, that video and audio generated by Project Genie carry SynthID watermarks, and that model inputs and outputs undergo safety screening. DeepMind calls Genie 4 its most realistic and interactive world model to date, and says it integrates real-time physics, reasoning, and audio; these are the company's own assessments, and no independent evaluation has yet confirmed its actual performance.
AI-written from the coverage · updated 3 d ago
Developments
2 developments
- Nov 19 02:13 · 4 reportsGenie 4 launches in Project GenieGoogle DeepMind: DeepMind opens Genie 4 world model to Google AI Ultra subscribers
- Oct 28 00:01 · 3 reportsGoogle DeepMind releases Genie 4 world modelGoogle DeepMind: DeepMind unveils next-generation world simulation model Genie 4
Coverage timeline
Follow the coverage to see the story from different sides.
- The DecoderPickGoogle DeepMind releases Genie 4 with chainable worlds and a community gallery
Google DeepMind released the world model Genie 4, moving it from research preview to availability for Google AI Ultra subscribers. It supports real-time text commands to change weather, characters, or plot, and generates native real-time sound effects that change with the scene.
- Demis HassabisPickDeepMind releases Genie 4 interactive world model, Ultra subscribers can try it in Project Genie
DeepMind released interactive world model Genie 4, which the company says integrates real-time physics, reasoning, and audio capabilities. Eligible Ultra subscribers can try it in Project Genie; see the official blog for details.
- Google DeepMindPickGoogle DeepMind launches Genie 4 in Project Genie with native audio and real-time editing
Google DeepMind announced that Genie 4 is now available in Project Genie, adding native audio, real-time editing, and an agent that helps create interactive virtual worlds.
- Google DeepMindPickDeepMind opens Genie 4 world model to Google AI Ultra subscribers
Google DeepMind has rolled out a new version of Project Genie to eligible Google AI Ultra subscribers, opening up the Genie 4 world model for the first time; users can enter prompts during exploration to change the weather, add characters or alter the story direction in real time, and it is paired for the first time with real-time native audio that changes with the scene.
- Demis HassabisPickDeepMind unveils Genie 4 world model, integrating real-time physics, reasoning and audio
Google DeepMind has launched Genie 4, an interactive world model that brings together real-time physics, reasoning and audio. The official announcement quoted describes it as the most realistic and interactive world model to date. Users can explore dynamic environments in real time, and the scenes, sounds, and the characters' actions, reactions and speech all change accordingly.
- Google DeepMindPickDeepMind releases Genie 4 world model
DeepMind has released Genie 4, which it calls its most realistic and interactive world model yet. According to the original post, users can explore dynamic environments in real time, observing how the scene responds and sounds, as well as how characters move, react, and speak.
- Google DeepMindPickDeepMind unveils next-generation world simulation model Genie 4
Google DeepMind has unveiled Genie 4, a next-generation world model that generates interactive simulated worlds in real time, with native audio and conversational interaction. Users can change the weather or camera angle, or add characters and objects, using natural language, and Gemini adjusts prompts to keep the scene coherent. It is currently available as a research preview to trusted testers. Google AI Ultra subscribers and early Gemini API partners will gain access in the coming weeks, though visual detail and object persistence may still drift over time.
Heat trend for this story
- Current (comparable)
- 5
- Peak (comparable)
- 20Nov 19 04:00
- 24-hour change
- -50%
The trend only compares participants observed continuously and completely, so it may cover fewer than the current heat count. Hover over or tap the chart to see each hour's heat; with a keyboard, use the left and right arrow keys.