AI Research Atlas

Qwen3.8-LiveTranslate (and Qwen3.5-LiveTranslate)

Alibaba (Qwen) · 18 September 2026

Simultaneous interpretation model using an interleave architecture; average latency cut from 2.8 s to 2.3 s, with speaker naming.

Rebuilds live translation around an interleaved architecture. The earlier Qwen3.5-LiveTranslate (2026-05-19, built on Qwen3.5-Omni) added visual context for better accuracy.

Date
Friday, 18 September 2026
Lab
Alibaba (Qwen)
Kind
model
Access
closed API

Figures

MeasureValueMeasured by
Average translation latency2.3 s (from 2.8 s)
Qwen3.5-LiveTranslate released 2026-05-19
company

Access mode inferred (no HF repo in the Qwen listing).

Sources

  1. releasebot.io/updates/qwen

This record was checked against its sources on 6 October 2026. How we check

Related