←back to thread

VibeVoice: A Frontier Open-Source Text-to-Speech Model

(microsoft.github.io)
448 points lastdong | 1 comments | 03 Sep 25 10:44 UTC | HN request time: 0.394s | source
Show context
rafaelmn ◴[03 Sep 25 11:59 UTC] No.45114707[source]▶
The Spontaneous Emotion dailog sounds like a team member venting through LLMs.

They could have skipped the singing part, it would be better if the model did not try to do that :)

replies(2): >>45114737 #>>45115881 #
1. eibrahim ◴[03 Sep 25 12:04 UTC] No.45114737[source]▶
Hahahah. Thats what I thought too