←back to thread

Show HN: Dia, an open-weights TTS model for generating realistic dialogue

(github.com)
652 points toebee | 1 comments | 21 Apr 25 17:07 UTC | HN request time: 0.205s | source
Show context
xienze ◴[21 Apr 25 17:51 UTC] No.43754550[source]▶
How do you declare which voice should be used for a particular speaker? And can it created a cloned speaker voice from a sample?
replies(1): >>43754643 #
1. toebee ◴[21 Apr 25 18:00 UTC] No.43754643[source]▶
You can add an audio prompt and prepend text corresponding to it in the script. You can get a feel for it by trying the second example in the Gradio interface!