SOURCE-LINKED INTELLIGENCE

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and linguistic cues, while video interaction also requires grounding the conversation in evolving visual context. We present Realtime-Venus, a proactive full-duplex interaction system with two separately trained 9B models: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for spoken interaction. Each model serves as a complete conversational frontend, integrating continuous perception, conversational control, and native speech

Read original source ↗ Open in workspace

recordType

paper

region

Global