DeepL's Aure model carries speaker tone into real-time translation
Original title: DeepL wants real-time translation to finally capture sarcasm and mood shifts
Aure runs in DeepL Voice meetings, in-person mode, and the API across eight languages, replacing a static voice sample.
DeepL released Aure for DeepL Voice so real-time translations transfer tone, emotion, emphasis, and speaking pace instead of using a voice sample captured at the start. The model continuously analyzes translated text and the original audio, and reinforcement learning is used to keep accents out of the output. At launch it supports English, German, Spanish, French, Italian, Japanese, Portuguese, and Korean.
- DeepL first rolled out voice preservation in September.
- DeepL acquired the Mixhalo team to strengthen real-time speech translation.
- Block recently unveiled Dessa, a speech model for detecting emotion and sarcasm.
- In May, DeepL cut about 250 jobs while restructuring around AI-powered teams.
- Vendors
- DeepL
- Products
- DeepL Voice
- Organizations
- Block
From the original article
1 min read at the-decoder.com
DeepL Voice's real-time translations are about to sound a lot more natural. The company's new Aure model carries over tone, emotion, emphasis, and speaking pace from the original speaker's voice into the target language. The article DeepL wants real-time translation to finally capture sarcasm and mood shifts appeared first on The Decoder.
By Jonathan Kemper · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.