Model Releases

Qwen3.5-LiveTranslate: from sound to vision, from words to accuracy

Original title:Qwen3.5-LiveTranslate: From Sound to Sight, From Word to Right

AI summary

Qwen3.5-LiveTranslate-Flash is the latest simultaneous interpretation model in the Qwen family, built on the Qwen3.5-Omni architecture and supporting real-time multimodal translation (audio, video, and visual context). Language coverage has expanded significantly: input audio and output text increased from 18 to 60 languages, and output audio from 10 to 29. Using Readable Unit technology, average end-to-end latency per token drops to 2.8 seconds, a reduction of 3.45 seconds in first-token latency and 1.88 seconds in per-token latency compared with the previous generation. It supports one-sentence-initiated real-time voice cloning and dynamically configurable hotword enhancement. On the FLEURS and CoVoST2 benchmarks, translation accuracy surpasses mainstream commercial large speech models.

Key Takeaways

  • 5-LiveTranslate-Flash is the latest simultaneous interpretation model in the Qwen family,built on…
  • 5-Omni architecture and supporting real-time multimodal translation (audio,video,and visual…
  • Language coverage has expanded significantly: input audio and output text increased from 18 to 60…
  • Using Readable Unit technology,average end-to-end latency per token drops to 2.
  • 8 seconds,a reduction of 3.

Quick Facts

Published
Updated
Source
Qwen:Blog Retrieval(API)
Category
Model Releases
AI score
77
Read the original Read the full article at the original source
Why it matters

这个版本让同声传译从“能用”变成了“好用”,语言覆盖从 18 跃升 60,延迟压到 2.8 秒,加上视觉消除歧义,做国际业务和直播的人值得跟进。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Qwen3.5-LiveTranslate: from sound to vision, from words to accuracy. May 19, 2026. https://new.nat6.net/en/news/cmpcs39q504wrslae56ztkjwi/

View all →