Google launches Genie 4, its most realistic interactive world model with native audio
sundarpichai · x · 2026-10-28
Sundar Pichai announced Genie 4, which Google calls its most realistic and interactive world model.
Key capabilities:
- Steer dynamic environments in real time, shaping events, camera angles, and actions
- Generate native audio matched to the world, from background sounds to characters that converse in real time
- Simulate photorealistic scenes and real-world physics
- Produce more coherent multi-step events via Gemini-powered reasoning
It's rolling out now as a research preview to trusted testers, with upcoming access for Google AI Ultra subscribers via Project Genie and for early partners through the Gemini API and AI Studio.
Related event: DeepMind Unveils Genie 4, Its Most Interactive World Model(17 posts)→
More from Models
- X referral program pays in Grok usage resets with no cap — and Cursor is in its exclusion list — faraz0x · 2026-10-28
- Leak: DeepMind's Genie 4 is a real-time world model with native audio and type-to-edit scenes — rohanpaul_ai · 2026-10-28
- NVIDIA Launches Post-Training Nemotron for Europe via Nemotron Labs — NVIDIAAI · 2026-10-28
- AI model prices today mirror Uber's subsidized early days, may rise sharply later — pstAsiatech · 2026-10-28
- AI text detector posts 99.8% Arabic accuracy with under 1% false positives across languages — markjeffrey · 2026-10-28
- Day 1 of AI model competition livestream: Gemini takes clear lead — my_cat_can_code · 2026-10-28