Google DeepMind launches the world model Genie 4, supporting synchronous generation and real-time editing of audio and video
Google DeepMind has launched the world model Genie 4, which is currently in the research preview phase. It can generate interactive virtual worlds and modify scenes by inputting prompts during runtime, as well as generate real-time audio synchronized with the visuals. Compared to the previous Genie 3, Genie 4 has improved visual realism and supports real-time adjustments of weather, camera angles, and adding or deleting characters and objects. It can maintain a continuous scene for up to two minutes, twice as long as the previous generation.
Same story — featured version shown《Google DeepMind releases world model Genie 4》
Same story6 other outlets also reported this
How the accounts differ:The Verge states the model supports up to two minutes of scenes, while Ars Technica and TechCrunch mention improvements in physics and character simulation but do not specify the scene duration.
- The Verge · AI··First
Google Genie 4 World Model Released: Supports More Realistic Interactive Experience
- Ars Technica · AI··+0 min
DeepMind releases Genie 4 world model, claims physics and character simulation are more realistic
Adds:DeepMind mentions the model's integration with Gemini AI and the use of Gemini 4 Argon for task decomposition.
- Google DeepMind··+2 min
Google DeepMind releases world model Genie 4
Adds:Google DeepMind notes the model's ability to generate native audio and voice dialogue.
- TechCrunch · AI··+31 min
Google DeepMind released the Genie 4 world model, adding audio and real-time editing.
Adds:TechCrunch mentions the model's integration with Gemini AI and the use of Gemini 4 Argon for task decomposition.
- The Decoder··+1 h 25 min
DeepMind Genie 4 Released: Exploring the Frontier of Modern Intelligent Agent Design
Adds:The Decoder mentions the integration with SynthID for watermarking AI-generated content.
- ITHome · AI··+7 h 5 min·Reading now
Google DeepMind launches the world model Genie 4, supporting synchronous generation and real-time editing of audio and video
- ITHome · AI··+7 h 42 min
Google DeepMind releases Genie 4 world model, supporting real-time natural language rewriting and native audio
- ITHome · AI··+7 h 56 min
- MarkTechPost··+15 h 35 min
Google DeepMind Releases Genie 4 Real-Time World Model, Natively Generating Audio
In order of publication · later reports are added as they appear · Compared by AI from each outlet’s title and summary
Source: ITHome · AI · ithome.com