Models84°
Google 发布 Genie 4：首个原生音频实时世界模型
Why we picked it
Google 把 Genie 3 的 1 分钟会话拉到 2 分钟，还让 Gemini 3.8 Flash 当向导实时引导场景，想玩交互式生成的可以去排队了。
Google 发布 Genie 4，是其首个能原生生成音频的实时世界模型，支持随场景变化的自适应交互对话。Gemini 3.8 Flash 作为引导智能体观察场景、拆解目标并实时流式输出更新。单次会话时长提升至 2 分钟，是 Genie 3 的两倍。目前开放等候名单注册。
Original · @koltregaskes
Google announced Genie 4, their first real-time world model to generate audio natively, including interactive dialogue that adapts on the fly.
Gemini 3.8 Flash acts as a guiding agent that observes the scene, breaks goals into steps, and streams updates in real time.
Sessions now last up to 2 minutes, double the amount of time of Genie 3.
Sign up for the waiting list below. https://t.co/Gt5nFAmt72
