aifollow.news
Search
Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.
Genie 4 generates ambient sound, music and dialogue from characters that respond to users and events in the scene. Users can change the weather, move the camera or add people by typing, while Gemini keeps the running scene coherent. Access starts with trusted testers before Google AI Ultra subscribers and early Gemini API partners.
> Genie 4 是 Google DeepMind 首个原生支持音频的实时世界模型，能够生成环境音、音乐，以及会对用户和模拟世界中的事件作出反应的角色的实时对话。
> 用户可以通过输入文字改写正在运行的模拟场景，改变天气、移动摄像机或添加人物；Gemini 会让每项修改契合场景并保持连贯。
> Gemini 3.8 Flash 充当循环中的导演，将目标拆分为步骤并检查传入的画面；Gemini 4 Argon 利用这一循环，模拟了 Apptronik 的 Apollo 人形机器人下跳棋。
> 访问权限将首先向受信任的测试人员开放，随后向 Google AI Ultra 订阅用户和早期 Gemini API 合作伙伴开放。https://t.co/DYN0zqMU97
Name a person, company or topic. We find the sources and gather every new development in your own tab.
