Realtime-Venus: A full-duplex interaction system with asynchronous delegation
Realtime-Venus introduces two 9B full-duplex interaction models (Omni and Audio) that outperform Gemini 3.1 Live and GPT-4o on continuation metrics.
Realtime-Venus is a proactive full-duplex interaction system built on two separately trained 9B models: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for spoken interaction. A dual-loop runtime lets foreground interaction continue while Realtime-Venus-Harness asynchronously executes background reasoning and tool tasks. Realtime-Venus-Omni leads on six of eight video benchmarks, including StreamingBench (70.2%), OVO-Bench (64.7%), and Daily-Omni (81.3%), while Realtime-Venus-Audio tops MMAU (78.0%) and MMAU-Pro (63.2%). On Full-Duplex-Bench v1.5, Realtime-Venus-Audio handles 75% of interruptions and exceeds Gemini 3.1 Live and GPT-4o on all three continuation metrics.
- Two 9B models handle full-duplex audio-visual and spoken interaction on a shared causal timeline
- Dual-loop runtime delegates background reasoning and tool execution asynchronously via Realtime-Venus-Harness
- Realtime-Venus-Omni tops six of eight video benchmarks including StreamingBench 70.2% and Daily-Omni 81.3%
- Realtime-Venus-Audio exceeds Gemini 3.1 Live and GPT-4o on all three continuation metrics
From the original article
1 min read at huggingface.co
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.
By Ruixiang Zhao, Hualei Wang, Renhe Sun · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.