[Alibaba Qwen Releases Qwen3.8-LiveTranslate, Reducing Latency to 2.3 Seconds Across 60 Languages] DeepFlow Tech News: On September 19, Alibaba Qwen unveiled the next-generation real-time simultaneous interpretation model, Qwen3.8-LiveTranslate. Based on the Interleave architecture, it reduces the average latency (LAAL) across 60 languages from 2.8 seconds to 2.3 seconds. The official announcement also stated that the new model has improved in three key metrics: fidelity, fluency, and conciseness. This release marks another iteration for Qwen in simultaneous interpretation scenarios, with latency data being the primary point of improvement.