Genie 4
Google DeepMind announced Genie 4, a world model that generates interactive simulations with native audio, music and dialogue, now in research preview for trusted testers.
Genie 4 is natively multimodal, so music, ambient sound and character dialogue are generated together with the world. It builds on Gemini models, with Gemini Omni anchoring real-world appearance and other Gemini models helping keep the simulation coherent. Users steer scenes in real time with keyboard controls and text prompts.
- Date
- Tuesday 27 October 2026
- Lab
- Google DeepMind
- Kind
- model
- Access
- research preview
Rollout starts with trusted testers, then Google AI Ultra subscribers in Project Genie and early access Gemini API and Google AI Studio partners. A waitlist is open.
Sources
- deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/
- timesofindia.indiatimes.com/technology/tech-news/google-deepmind-launches-genie-4-ceo-sund
- ndtvprofit.com/technology/google-unveils-genie-4-an-ai-that-builds-interactive-worlds-with
This record was partly confirmed: some claims could not be checked on 27 October 2026. How we check