Release dates
— Genie 4 entered research preview with trusted testers for interactive world generation and native video and audio output; broader user and developer access is still forthcoming. ↗
Genie 4
Google DeepMind’s interactive world-generation model, which uses text and camera controls to change a scene in real time and natively generates video and sound.
Currently available as a research preview to trusted testers. Google says it plans to expand to Google AI Ultra subscribers in Project Genie and early-access partners in Gemini API / AI Studio; those plans are not recorded as current GA.
MODEL NUMBER152
- First public date
- 2026-10-27
- Organization
- Google DeepMind
- Family
- Genie
01
Specifications
Only published specifications are shown.
- Input modalities
- Text · Image
- Output modalities
- Video · Audio
- Open weights
- No
- Status
- Preview
02
Overview
Why it mattered
Genie 4 extends video generation into interactive world simulation. Google presents creative and scenario-simulation uses; robotics training is described as a downstream application, not as the model’s release category.
03
Architecture & capabilities
Model capabilities
Video generationAudio generationCamera control
04
Release history
Genie 4 entered research preview with trusted testers for interactive world generation and native video and audio output; broader user and developer access is still forthcoming.
View source05
Related models
Select a card to view the related model.
No related models recorded yet
06
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.