{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/genie-4/","md":"https://postcutoff.com/m/genie-4/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"genie-4","name":"Genie 4","org":"Google DeepMind","family":"Genie","released":"2026-10-27","status":"preview","type":"world-model","modality_in":["text","image"],"modality_out":["video","audio"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Project Genie (Google Labs)","url":"https://labs.google/projectgenie","docs":"https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/"},{"provider":"Gemini API / Google AI Studio (early-access partners, waitlist)","docs":"https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/"}],"capabilities":[{"name":"Native real-time audio in a world model","detail":"DeepMind's first real-time world model to generate audio natively: ambient sound, music and interactive dialogue with characters.","first":false,"discovered":"launch","source":"https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/"},{"name":"Text steering of a running simulation","detail":"Free-form prompts change weather, camera angle or add people/objects mid-session; Gemini adapts the prompt to the scene.","first":false,"discovered":"launch","source":"https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/"},{"name":"Gemini-directed multi-step events","detail":"Gemini 3.8 Flash plans steps and verifies frames; Gemini Omni anchors real-world appearance; scenes stay consistent up to ~2 minutes (TechCrunch).","first":false,"discovered":"launch","source":"https://techcrunch.com/2026/10/27/googles-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering/"}],"entry":"2026-10-27-genie-4-world-model","notes":"Research preview for trusted testers from 2026-10-27; 'in the coming weeks' for Google AI Ultra subscribers via Project Genie and Gemini API / AI Studio early-access partners. No public model id, price, resolution or frame rate published. Output carries SynthID.","verified":"2026-10-28","body_md":"Successor to [Genie 3](/m/genie-3/). Not generally callable yet; join the waitlist from the DeepMind post.\n\nSources: [DeepMind blog](https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/), [TechCrunch](https://techcrunch.com/2026/10/27/googles-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering/).","page_url":"https://postcutoff.com/m/genie-4/","standing":{"kind":"world","newer_count":0,"newer":[],"before":{"id":"genie-3","name":"Genie 3","org":"Google DeepMind","released":"2025-08","page_url":"https://postcutoff.com/m/genie-3/"},"after":null,"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights."}}