Alibaba Qwen Team Releases Qwen3.8-LiveTranslate: A Real-Time Interpretation Model That Cuts Average Lag to 2.3 Seconds Across 60 Languages
2.3 seconds. Alibaba's Qwen just shipped real-time simultaneous interpretation across 60 languages—a capability frontier labs have been racing on.
Why it matters
Alibaba's new Qwen3.8-LiveTranslate represents a meaningful advance in multimodal capability (speech-to-speech interpretation with low latency, speaker diarization, and long-context understanding), shipped and available now. It's a model release that changes the frontier benchmark for real-time translation and interpretation.
The key facts
7 to knowQwen3.8-LiveTranslate reduces average lag (LAAL) from 2.8s to 2.3s
Supports 60 input languages, 29 output languages
Features real-time speaker diarization with stable voice cloning
Built on new Interleave architecture for simultaneous interpretation
Available now via WebSocket API on Alibaba Cloud Model Studio and QwenCloud
Includes synchronized bilingual display and long-context disambiguation for names/terms
Published September 2026 — recent release
Go to the source
MarkTechPostmarktechpost.com
Publisher excerpt: Qwen has released Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model built on a new Interleave architecture. It cuts average lagging (LAAL) from 2.8 seconds to 2.3 seconds. It also adds real-time speaker diarization with stable voice cloning, synchronized bilingual display, and…