Google releases Genie 4 for real-time interactive world generation
In short: Google has launched Genie 4, an advanced world model available to Google AI Ultra subscribers that enables users to create and edit interactive environments in real time. The update introduces native adaptive audio, 360-degree panorama grounding, and a new Project Genie agent for conversational environment creation.
This summary was generated automatically by AI from Google DeepMind's publication. It is our own text, not a copy of the original — facts, figures and quotes belong to the source, linked above and below.
What changed?
- 1Genie 4 model release for real-time, interactive environment generation
- 2Introduction of native adaptive audio tied to visual scenes
- 3Genie 3 updates: increased session length to 3 minutes and 360-degree panorama grounding
- 4New Project Genie agent for natural language-based world building
- 5Community gallery for publishing and remixing interactive worlds
| Parameter | Before | Now |
|---|---|---|
| Session duration | 60 seconds (Genie 3) | 3 minutes (Genie 3) |
| Audio capability | Not specified | Real-time native adaptive audio |
| Grounding | Not specified | 360-degree panorama image grounding |
Why it matters
This release advances the frontier of interactive, multimodal generation by allowing users to shift physics, weather, and characters in real time through text prompts. The integration of adaptive audio and the ability to link environments creates more complex, persistent interactive experiences.
Sources
- Google DeepMindOfficialPrimary sourceOriginal article →„Genie 4 is now available“18 Nov 2026, 20:13
- Published by source
- 18 Nov 2026, 20:13
- Found by our system
- 18 Nov 2026, 20:27
- Summary generated
- 18 Nov 2026, 20:59
This article was written by AI from the original source. Facts, numbers and prices come from the source; missing values are marked “Not specified”. Legal notice, copyright and privacy