Genie 4 is now available
Genie 4 launches for Google AI Ultra subscribers, delivering the most realistic and interactive world model yet with real‑time text‑prompted environment edits and native audio that adapts on‑the‑fly. The update also adds Genie 3 enhancements—sessions up to 3 minutes, 360° panorama grounding, and linked world sequences—for longer, panoramic experiences. Engineers can now embed conversational world‑building via the new Project Genie agent and share creations through a community gallery, opening new avenues for AI‑driven immersive content pipelines.
⚡ Key Takeaways
- Genie 4 enables real‑time environment editing via natural‑language prompts and streams adaptive native audio.
- Genie 3 now supports up to 3 minutes per generation (up from 60 seconds) and 360° panorama‑seeded world grounding.
- World chaining lets multiple generated worlds be linked for extended journeys.
- The Project Genie agent assists users in building custom worlds through simple conversational interactions.
- Published worlds can be shared, explored, and remixed in a community gallery.
Real‑time, promptable world generation with audio lets engineers create dynamic immersive experiences without pre‑rendered assets, accelerating prototyping and user‑generated content loops.
✅ Practical Steps
- Access Genie 4 by logging into the Project Genie website as a Google AI Ultra subscriber and select the Genie 4 model in the model picker.
- Use natural‑language prompts during navigation to modify weather, add characters, or trigger events, and observe native audio adapting in real time.
- Publish your generated world via the community gallery to enable remixing and discovery by other users.
Want the full story? Read the original article.
Read on Google DeepMind ↗