Skip to content
The Decoder· Jonathan Kemper·· 6d agoAI score70

DeepL Releases New Voice Model, Real-time Translation Captures Irony and Emotional Changes

DeepL wants real-time translation to finally capture sarcasm and mood shifts

AI digest

DeepL released the new voice model Aure, which can convert the tone, emotion, emphasis, and speaking speed in the original voice into the target language, thus achieving more natural real-time translation. The model supports English, German, Spanish, French, Italian, Japanese, Portuguese, and Korean.

Source:The Decoder · the-decoder.com