←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: 0.23s | source
1. lxe ◴[03 Sep 25 16:06 UTC] No.45117377[source]▶
There are 2 "best" TTS models out right now: HiggsAudio and VibeVoice. I found that Higgs is both faster and much higher fidelity than Vibe. Can't speak to expressiveness, but don't sleep on it.