DeepL launches Aure model that preserves tone and emotion
What happened
On November 11, The Decoder reported that DeepL launched a new model, Aure, to make DeepL Voice's real-time speech translation sound more natural. It carries the original speaker's tone, emotion, stress and pace into the target language, and picks up sarcasm and shifts in mood. The old approach took only a static voice sample at the start of a conversation; Aure keeps analyzing the translated output against the original audio throughout. In training, the model handled voice identity, intonation and content separately, and used reinforcement learning to avoid accented output.
Written by AI from the coverage · updated 13 hours ago
Coverage
Follow the reports to see the story from different sides.
- The DecoderDeepL wants real-time translation to finally capture sarcasm and mood shifts
DeepL 的新模型 Aure 将原说话者的语气、情绪、重音和语速传递到目标语言，让 DeepL Voice 的实时翻译更自然。旧方案只在对话开始时采集静态声音样本，Aure 则随对话持续分析译文和原始音频，训练时分别处理声音身份、语调和内容，并通过强化学习避免输出带有口音。
Heat over time
Heat now 7·Comparable peak 10（Nov 11 23:00）·Comparable change over 24 hours –
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.