DeepL 发布语音模型 Aure：实时翻译同步保留语气与语速、首发支持 8 种语言、已上线三款 DeepL Voice 产品
德国科隆 — DeepL 2026 年 11 月 11 日经 PRNewswire 发布语音模型 Aure，公司称这是其迄今最具动态感、最逼真的语音人工智能模型。Aure 为 DeepL Voice 实时语音翻译产品提供动力，能持续调整译出语音，反映说话人语气、情绪、重音与语速的变化。
公司表示，Aure 同时利用译出文本和原始音频，持续适应说话方式的变化，让译后语音保留原说话人的表达细微差别。公司另表示，Aure 是在其近期推出的语音保留技术基础上发展而来。
可用范围方面，Aure 的新能力自动生效、无需额外配置，覆盖三款产品：DeepL Voice 线上会议版、DeepL Voice 面对面对话版和 DeepL API for Voice。首发支持 8 种语言：英语、德语、西班牙语、法语、意大利语、日语、葡萄牙语和韩语，公司表示后续将增加更多语言；其他语言继续由 DeepL Voice 现有语音模型支持。
发布未给出定价。本稿以 DeepL 11 月 11 日发布正文为准。
DeepL Unveils Aure, a Voice Model That Carries Tone, Emphasis and Pace into Real-Time Translation: Eight Languages at Launch, Now Live Across Three DeepL Voice Products
Cologne, Germany — DeepL unveiled Aure via PRNewswire on November 11, 2026, calling it its most dynamic and lifelike Voice AI model yet. Powering DeepL Voice, the company real-time AI voice translation product, Aure continuously adapts translated speech to reflect changes in how someone is speaking, from shifts in tone and emotion to changes in emphasis and pace.
The company said Aure uses both the translated words and the original audio, so translated speech mirrors the nuances of human expression across languages in real time. The release said Aure builds on the company recent launch of voice preservation technology.
The new Aure capabilities are applied automatically, with no additional configuration required, across DeepL Voice for Online Meetings, DeepL Voice for In-Person Conversations and the DeepL API for Voice. The model initially supports eight languages: English, German, Spanish, French, Italian, Japanese, Portuguese and Korean, with more languages to follow. DeepL Voice will continue to support other languages through its existing voice models.
The release gave no pricing. All details follow the text of the DeepL release dated November 11, 2026.
来源：DeepL
发布：GSM·美国（发布链接）
图片来源：图：图中是一名配音人员在录音棚话筒前工作。图中是录音棚配音工作的实物照片，为语音翻译题材通用配图，非该公司产品界面。Alexis Kasperavicius，CC BY-SA 2.0，经Wikimedia Commons。 / Photo: file photo. Alexis Kasperavicius, CC BY-SA 2.0, via Wikimedia Commons.
GSM Global · 本篇英文版 English edition of this story