Tavus Blog·· 15 天前精选评分74
Tavus 用状态空间模型解析 Phoenix-4.5：毫秒级实时情感与面部行为生成
view allAI, News, and EthicsState Space Models, Explained Through CodePhoenix-4.5 is the first real-time model to generate and control emotional states, active listening behavior, and continuous facial motion as a single, unified system. It is a real-time behavior generation engine, built from the ground up, that goes beyond photorealism to transform conversation data into emotionally responsive, context-aware facial expression and head motion with millisecond-level latency.Karthik Ragunath Ananda KumarJune 8, 2026
导读
Phoenix-4.5 是首个将情感状态生成、主动倾听行为与连续面部动作统一为单一系统的实时模型，文章以代码讲解其状态空间建模实现，覆盖毫秒级延迟的上下文感知表情与头部动作。
推荐理由
实时数字人行为生成的技术深度文，披露模型架构思路与延迟水平。
来源：Tavus Blog · tavus.io