Alibaba's Qwen has officially released the Qwen3.8-LiveTranslate simultaneous interpretation model, which supports 60 languages and uses an Interleave architecture. The update reduces word latency from 2.8 seconds to 2.3 seconds while improving accuracy, fluency, and conciseness across real-world application scenarios.
The coverage focuses on technical architecture and benchmark performance metrics, highlighting how structural changes in AI translation models aim to reduce latency and improve speaker preservation.
AI-generated from the sources below. Always check the originals.
Chinese tech media detail the technical architecture, including the Thinker-Talker dual module design and performance improvements across 60 languages.
Summaries are AI-generated from the linked sources and may contain errors; always check the originals. We summarise and link; we never republish articles. Photos come from openly licensed libraries, official publicity material and brand logos, credited to their sources. If you own an image and want it credited differently or removed, email info@coda.news and we will act promptly.
