DeepL's voice translation model that reproduces dynamic speaker traits such as intonation, emotion, stress and pacing in real ti
DeepL unveiled Aure, a voice AI translation model that powers DeepL Voice and reproduces a speaker's intonation, emotional shifts, stress and pacing in real time. Built on DeepL's voice-preservation technology, Aure launches with eight languages including English, German, Spanish, French, Italian, Japanese, Portuguese and Korean, but not Chinese, and is available across web meetings, face-to-face mode and the Voice API.
DeepL has unveiled Aure, a new model for its Voice real-time translation product that carries the original speaker's tone, emotion, emphasis and speaking pace into the target language instead of relying on a static voice sample captured at conversation start. It decouples voice identity, speech melody and content during training and uses reinforcement learning to suppress accents, rolling out automatically across Online Meetings, In-Person Conversations and the API.