AI HOT (Curated Pool)Sep 18, 2026, 17:30 UTC+8

Qwen launches Qwen3.8-LiveTranslate real-time interpretation model with 2.3s latency and speaker separation

Qwen 发布 Qwen3.8-LiveTranslate 实时同传模型，LAAL 降至 2.3 秒

Qwen3.8-LiveTranslate cuts simultaneous interpretation latency from 2.8s to 2.3s by interleaving audio and text into a single stream. It supports 60 input languages, real-time speaker separation with voice cloning, and synchronized bilingual output. On the Omnilingua-MSpeaker benchmark it outperforms current mainstream systems in faithfulness, fluency, and conciseness. API is available via Alibaba Cloud DashScope.

Why it matters: Qwen ships a real-time interpretation model with 2.3s latency, speaker diarization, and bilingual subtitles — three new capabilities that push simultaneous interpretation beyond translation into scene understanding. Score stays below 85 because only the official blog is availa...

Read the original ↗Export Markdown

Take

The reason to click: Qwen pushed simultaneous interpretation latency down to 2.3s and added three features that make it usable in real meetings, not just demos. The Interleave architecture weaves audio and text into one stream so already-translated chunks get cached — that's where the quality bump and latency drop from 2.8s come from.

The practical upgrades: real-time speaker separation with voice cloning (so you know who said what), synchronized bilingual output on one screen, and long-context disambiguation that keeps names and terms consistent across a conversation. On Omnilingua-MSpeaker and FLEURS, it beats current mainstream systems on faithfulness, fluency, and conciseness.

I'd discount this a bit: 2.3s is average latency — the post doesn't break out performance on very long sentences or noisy environments. DashScope pricing isn't mentioned either. But if you need live bilingual captions for cross-border meetings or streams, this is worth a test call.

Source: AI HOT (Curated Pool) · qwen.ai
Published: Sep 18, 2026, 17:30 UTC+8 · 12 days ago