Generate high-quality danish speech from text with reference audio styling.
This is a preview of a model that was developed as part of the CoRal project, and is a finetuned version of the Chatterbox Multilingual.
💡 Note: Ensure that the reference clip matches the specified language tag. Otherwise, language transfer outputs may inherit the accent of the reference clip's language. To mitigate this, set the CFG weight to 0.