SOURCE-LINKED INTELLIGENCE

AVTR-1: Open Stack for Real-Time Interactive Avatars

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live system must synchronize the model's output with speech from an external voice agent, schedule video frames for playback, and handle interruptions. We introduce AVTR-1, an open stack for real-time interactive avatar conversations, built around a compact 153M-parameter autoregressive flow-matching motion generator conditioned on both participants' audio. We adapt its audio encoder for streaming through self-distillation. The stack turns the model's

Read original source ↗ Open in workspace

recordType

paper

region

Global