← All models

Qwen3-LiveTranslate-Flash

Published Publisher Alibabaqwen3-livetranslate-flash-2025-12-01

Overview

Qwen3-LiveTranslate-Flash is a multilingual audio and video translation model built on Qwen3-Omni infrastructure. It supports offline and real-time translation, using visual context to help interpret video. It accepts audio or video and can return translated text alone or text with speech. Suitable uses include translating recordings and multilingual audio-video content. (help.aliyun.com)

Capabilities and limits

  • The release announcement says the model understands 19 languages, speaks 10, and supports eight Chinese dialects. The current Chinese file-translation guide describes translation among 18 languages; consult the applicable API guide for supported language pairs. (help.aliyun.com)
  • Context window: 53,248 tokens; maximum input: 49,152 tokens; maximum output: 4,096 tokens. (help.aliyun.com)
  • The file-translation API supports a single user message and streaming output only; multi-turn conversation and system messages are not supported. The documented endpoint is compatible with the OpenAI chat completions protocol. (alibabacloud.com)

Release

The official release listing places this model under December 4, 2025. The ID identifies the December 1, 2025 snapshot. Official release announcement. (help.aliyun.com)

Pricing

Prices below are for this exact snapshot, per 1 million tokens, checked November 17, 2026. Input and output are billed separately by modality. Regional and platform listings are distinct and are not presented as currency conversions.

  • Alibaba Cloud China site, Beijing, CNY: audio input ¥10; image input ¥4; text output ¥10; audio output ¥40. The snapshot has no free quota. (docs.bailian.console.aliyun.com)
  • Alibaba Cloud China site, Singapore international deployment, CNY: audio input ¥11.573; image input ¥4.629; text output ¥11.573; audio output ¥46.292. (docs.bailian.console.aliyun.com)
  • Alibaba Cloud international site, Singapore international deployment, USD: audio input $1.577; image input $0.631; text output $1.577; audio output $6.308. The snapshot has no free quota. (alibabacloud.com)
  • Alibaba Cloud international site, Beijing, USD: audio input $1.434; image input $0.573; text output $1.434; audio output $5.734. (alibabacloud.com)

Official pricing sources: China-site pricing; international-site pricing. For implementation details, see the official API reference.