Qwen3-LiveTranslate-Flash:视、听、说全模态同传大模型

简介: 通义千问Qwen3-LiveTranslate-Flash推出实时多模态同声传译,支持18种语言及多种方言,融合视觉信息增强理解,实现3秒超低延迟、高精度语音翻译,适用于复杂环境下的跨语言交流。

Swipe for Chinese >>>

News Today

Qwen3-LiveTranslate-Flash: Real‑Time Multimodal Interpretation — See It, Hear It, Speak It

Qwen3-LiveTranslate-Flash delivers high‑precision, lightning‑fast and ultra‑reliable real‑time multilingual audio and video interpretation. With the extensive capabilities of Qwen3‑Omni and training on millions of hours of multimodal data, it enables both offline and live translation in 18 languages, making cross‑language communication seamless.

Key Features:

  • Multilingual and Dialect Coverage: Supports major official languages including Chinese, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean, Indonesian, Thai, Vietnamese, Arabic, Hindi, Greek, Turkish; as well as dialect and accent translation for Mandarin, Cantonese, Beijing, Wu, Sichuan, and Tianjin dialects.
  • Vision‑Enhanced Comprehension: For the first time, Qwen3‑LiveTranslate‑Flash incorporates visual context augmentation, enabling it to not only understand what it hears but also understand what it sees. By detecting and interpreting lip movements, gestures, on‑screen text, and real‑world entities, the system robustly handles noisy audio environments and resolves ambiguities in terms with multiple meanings.
  • 3s Latency: A lightweight mixture‑of‑experts architecture, coupled with dynamic sampling, enables simultaneous interpretation with latency as low as three seconds.
  • Lossless Interpretation: Utilizes semantic unit prediction to mitigate cross‑lingual reordering challenges in translation, achieving real‑time translation quality that is close to offline translation.
  • Natural Voice Quality: With training on massive speech datasets, the model delivers lifelike voices whose tone and expressiveness naturally follow the meaning of the source speech.

Performance

Qwen3‑LiveTranslate‑Flash achieves significantly higher accuracy than strong large-scale models, including Gemini‑2.5‑Flash, GPT‑4o‑Audio‑Preview, and Voxtral Small‑24B, on public benchmarks for Chinese, English and multilingual speech translation.

Qwen3‑LiveTranslate‑Flash consistently delivers leading translation performance across different domains and under challenging acoustic conditions.

Semantic unit prediction technology alleviates cross-lingual reordering issues, enabling real-time simultaneous interpretation to significantly reduce latency while maintaining over 94% of the accuracy achieved by non-real-time translation.

Visual enhancement technology further improves Qwen3-LiveTranslate-Flash’s translation precision in challenging scenarios such as noisy audio, ambiguous word meanings, and proper noun translation. In real-time settings, visual information compensates for missing speech context, making its advantages even more pronounced.

Examples

1 Speech‑to‑Speech Simultaneous Translation

Local API Test: real‑time interpretation | English → Chinese

2 Vision‑Enhanced Speech Translation

Homophones / Ambiguous Terms | English → Chinese

What's Next

Qwen will keep advancing the accuracy, naturalness, and emotional fidelity of our speech translation; extend coverage to more languages; and reinforce its robustness across varied and challenging acoustic environments. The goal is to bridge linguistic divides, enabling conversations to flow as smoothly and naturally as if speaking face to face.

/ END /

来源  | Alibaba Cloud Internationa公众号


相关文章
|
5月前
|
API 语音技术 Python
一条命令跑起实时同传:Qwen3.5 LiveTranslate 浏览器 Demo 开源了
通义千问Qwen3.5 LiveTranslate浏览器端开源Demo,30秒体验超低延迟(2.5s首字)实时同传:支持60语种识别、29语种音色克隆语音输出、热词增强、视觉消歧,开箱即用。含完整WebSocket协议实现,助力快速集成。
1789 2
|
存储 人工智能 测试技术
图像相似度比较之 CLIP or DINOv2
图像相似度比较之 CLIP or DINOv2
|
人工智能 移动开发 自然语言处理
阿里云百炼产品月刊【2025年9月】
本月通义千问模型大升级,新增多模态、语音、视频生成等高性能模型,支持图文理解、端到端视频生成。官网改版上线全新体验中心,推出高代码应用与智能体多模态知识融合,RAG能力增强,助力企业高效部署AI应用。
2649 0
|
10月前
|
机器学习/深度学习 人工智能 自然语言处理
AI数字人厂商的技术发展与行业生态分析
AI数字人融合语音识别、自然语言处理与3D建模等技术,正加速应用于金融、教育、医疗等领域。依托大模型与多模态交互,实现拟人化智能服务。世优科技推出“波塔AI数字人”,支持定制化形象与实时交互,助力政企数字化升级。行业快速发展的同时,也面临隐私、伦理与标准化挑战,需多方协同推进。
|
人工智能 语音技术 流计算
一图掌握通义千问:模型生态与应用场景全览
通义千问(Qwen)系列提供全栈开源AI能力,涵盖语言、视觉、语音等多模态应用。旗舰模型Qwen3-Max性能领先,支持92种语言翻译与高精度语音识别,具备强大代码生成与图像处理能力,助力开发者与企业高效构建智能应用。
1561 2
一图掌握通义千问:模型生态与应用场景全览
|
机器学习/深度学习 自然语言处理 API
Qwen-MT:翻得快,译得巧
今天,机器翻译模型Qwen-MT正式上线,支持92种语言互译,具备高度可控性与低延迟、低成本特点,适用于多种场景。开发者可通过Qwen API体验其强大翻译能力。
2173 15
|
11月前
|
编解码 人工智能 语音技术
📢 我们发布了新一代端到端语音交互模型 Fun-Audio-Chat!
通义百聆开源Fun-Audio-Chat(8B),支持端到端语音交互,具备情感感知与任务执行能力。在多榜单同尺寸模型中排名第一,支持高精度语音理解、情感识别与Function Call,高效低延迟,已全面开放代码与权重,欢迎体验!
3295 10
|
搜索推荐 API Python
DeepSeek-V3.1 发布,迈向 Agent 时代的第一步
今日发布DeepSeek-V3.1,支持混合推理架构,提升思考效率与Agent能力。编程与搜索智能体表现显著增强,API已升级并支持Anthropic格式,模型开源,上下文扩展至128K。
1406 5