←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: 0.233s | source
Show context
enodios ◴[21 Apr 25 23:05 UTC] No.43757481[source]▶
The audio quality is seriously impressive. Any plans to add word-level timing maps? For my usecase that is a requirement, so unfortunately I cannot use this yet, but I would very much like to.
replies(1): >>43758076 #
1. toebee ◴[22 Apr 25 00:49 UTC] No.43758076[source]▶
Thank you for the kind words! We don't have plans for that yet, but you can always open an issue or RP on Github.