Qwen launches Qwen3.8-LiveTranslate with 2.3-second latency

Qwen launches Qwen3.8-LiveTranslate with 2.3-second latency

N
News Editor
2026-09-19 07:57:22
Qwen has released Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model that cuts LAAL, a metric used to measure average translation lag, to 2.3 seconds from 2.8 seconds in the previous generation. The update also adds real-time speaker separation, synchronized streaming output for source and translated text, and long-context disambiguation. According to the source report, the model can identify different speakers, align translated output with specific speakers, and keep translated speech more consistent with each speaker’s voice characteristics. It also uses prior context to resolve names, terminology, and pronoun references, reducing ambiguity that can arise when only the current sentence is considered. API pricing is largely unchanged from the prior version. Alibaba Cloud’s pricing page shows that in the Beijing region, audio input, image input, text output, and audio output for Qwen3.8-LiveTranslate are priced the same as Qwen3.5-LiveTranslate. In Singapore, prices for those four items are slightly lower.

Qwen has released Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model that reduces LAAL, the metric used to track average translation lag, from 2.8 seconds in the previous generation to 2.3 seconds.

The new model adds real-time speaker separation, synchronized output for source and translated text, and long-context disambiguation. It can distinguish between different speakers, map translated content to the correct speaker, and keep translated speech more stable in preserving each speaker’s voice characteristics. Source text and translated text are also returned in a synchronized stream.

For context handling, Qwen3.8-LiveTranslate uses earlier dialogue to identify names, terminology, and references, cutting down on ambiguity that can appear when the model looks at only the current sentence.

API pricing is broadly unchanged from the previous generation. Alibaba Cloud’s pricing page shows that in the Beijing region, pricing for audio input, image input, text output, and audio output is identical to Qwen3.5-LiveTranslate. In Singapore, prices for the same four items are slightly lower.

This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan.
200

Disclaimer:

The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.

Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.