{"rewrite":{"id":"r_a8f8ee22d52168d683432a9f","clusterId":"c_09d9da0746217bfe3de12298","slug":"google-deepmind-announces-genie-4-an-ai-that-generates-virtual-worlds-in-real-time","model":"deepseek-v4-1-flash","headline":"Google DeepMind Announces Genie 4, an AI That Generates Virtual Worlds in Real Time","summary":"Google DeepMind announced Genie 4 on October 27, 2026. The world simulation AI generates virtual worlds in real time from user operations. Compared with earlier models, visuals and human movement are more realistic, and Genie 4 also generates environmental sounds and dialogue. Users move the camera by keyboard and change weather or add people and objects with text instructions.","whyItMatters":"Genie 4 moves world simulation from passable visuals toward physics, human motion and synchronized dialogue, and Google DeepMind names robot training and game development as its uses while acknowledging that object appearance and position can still drift during long generations.","webCardHtml":"\u003cp\u003eThe model is being provided to some testers now, with Google AI Ultra subscribers and early access partners of the Gemini API and Google AI Studio to follow. Genie 4 combines Gemini models with the generator: Gemini divides a task into steps and makes judgments, and Genie 4 generates the movement for each step, which Google DeepMind says makes complex actions possible. Demo footage includes a man playing saxophone on a lake with a freely moving camera, and a rural Japanese train station in the 1980s with passengers walking the platform and boarding trains. The company lists robot training and game development as intended applications, and says objects sometimes change appearance or position during long generations.\u003c/p\u003e","blueskyPost":"Google DeepMind announced Genie 4 on October 27, 2026. The world simulation AI generates virtual worlds in real time, now with more realistic human movement, environmental sounds and character conversations. Some testers have it; Google AI Ultra subscribers are next.","twitterPost":"Google DeepMind announced Genie 4 on October 27, 2026. The world simulation AI generates virtual worlds in real time, with more realistic human movement, environmental audio and character dialogue. Some testers have access; Google AI Ultra subscribers are next.","threadsPost":null,"newsletterBlurb":"Google DeepMind announced Genie 4 on October 27, 2026, a world simulation AI that generates virtual worlds in real time from keyboard and text input. Human movement is more natural and the model now generates environmental sounds and conversations that shift with user actions. It is with some testers now, with Google AI Ultra subscribers and Gemini API and Google AI Studio early access partners to follow.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20261028-google-genie-4/\",\"title\":\"Google Announces \\\"Genie 4,\\\" an AI That Generates Virtual Worlds in Real Time, Capable of Realistically Generating People's Movements and Conversations\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":5276,"outputTokens":714,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1793158472,"createdAt":"2026-10-28T03:29:26.000Z","publishedAt":"2026-10-28T03:33:26.000Z","updatedAt":"2026-10-28T03:33:26.000Z"},"cluster":{"id":"c_09d9da0746217bfe3de12298","canonicalTitle":"Googleが仮想世界をリアルタイムで生成するAI「Genie 4」を発表、人物の動きや会話もリアルに生成可能","representativeArticleId":"a_3eb14a04d7b1f1bea63d7353","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[\"Genie 4\"],\"studios\":[\"Google DeepMind\"],\"people\":[],\"type\":\"announcement\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-10-28T02:50:00.000Z","lastSeenAt":"2026-10-28T02:50:00.000Z","updatedAt":"2026-10-28T03:33:25.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20261028-google-genie-4/","title":"Googleが仮想世界をリアルタイムで生成するAI「Genie 4」を発表、人物の動きや会話もリアルに生成可能"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":["Genie 4"],"studios":["Google DeepMind"],"people":[],"type":"announcement","domain":"other","is_roundup":false},"keyFacts":["Google DeepMind announced Genie 4 on October 27, 2026.","Genie 4 generates virtual worlds in real time in response to user operations.","Genie 4 generates environmental sounds and conversations between characters.","Genie 4 is being provided to some testers, with Google AI Ultra subscribers and Gemini API and Google AI Studio early access partners to follow.","Google DeepMind names robot training and game development as intended uses."],"pageLinks":{"healthSlugs":["genie-4","google-deepmind"],"storySlugs":[],"entities":[{"slug":"genie-4","supported":0,"disputed":0,"contradicted":0,"unverified":3,"overall":"unverified","story_count":1,"has_dossier":false},{"slug":"google-deepmind","supported":4,"disputed":0,"contradicted":0,"unverified":12,"overall":"green","story_count":9,"has_dossier":true}],"stories":[],"entitiesOk":true,"storiesOk":true}}