Qwen (千问) launched Qwen3.8-LiveTranslate, a simultaneous-translation model using an Interleave architecture, reducing average per-character latency from 2.8 to 2.3 seconds.

The launch targets real-time simultaneous translation. A Telegram message attributed to the Qwen model team’s WeChat account reports the release of Qwen3.8-LiveTranslate on September 19. The announcement identifies Interleave as the architecture used to restructure its real-time translation approach.

The specific quantitative improvement concerns latency. The source labels its average per-character latency measure LAAL and reports a reduction from 2.8 seconds to 2.3 seconds. It does not provide the metric’s full definition or the evaluation conditions.

The announcement also claims improvements in accuracy, fluency, and conciseness. No numerical quality scores, supported-language list, model size, deployment hardware, or pricing are included in the supplied message. The reported latency should therefore not be treated as a measured result for every language pair or deployment environment.