Qwen ships LiveTranslate real-time interpreter with lag cut to 2.3s across 60 languages
Alibaba_Qwen · x · 2026-09-19
Alibaba's Qwen team released Qwen3.8-LiveTranslate, a next-gen real-time simultaneous interpretation model built on an Interleave architecture. It improves faithfulness, fluency and conciseness across 60 languages while cutting average lagging (LAAL) from 2.8s to 2.3s.
Key features:
- Real-time speaker diarization — separates speakers in multi-party speech, preserving each voice via more stable voice cloning
- Synchronized bilingual display — source and translation on screen together
- Long-context disambiguation — uses conversation history to keep names and terminology consistent
Available now via QwenCloud, with an accompanying blog post.
More from Multimodal
- Experimental video mixes visual styles, generated with Seedance 2.5 on Adobe Firefly — umesh_ai · 2026-11-04
- Hailuo AI claims H3 scored perfect on language tests; Japanese creator praises its Japanese signage fidelity — Hailuo_AI · 2026-11-04
- YANAMI: 400K-dialog multimodal dataset shows models still fail at stateful multiturn interaction — Shengyu Wang · 2026-11-04
- Open-source Idol model turns a single image into 3D in 45s on 8GB VRAM — Promptmethus · 2026-11-04
- ComfyUI v0.44.0 released with new Patina texture nodes — Fcking_Chuck · 2026-11-04
- Krea 3 technical report released: a deep dive into data, architecture and training — bdsqlsz · 2026-11-04