(microsoft.github.io)

448 points lastdong | 2 comments | 03 Sep 25 10:44 UTC | HN request time: 0.408s | source

Show context

Is there a current, updated list (ideally, a ranking) of the best open weights TTS models?

I'm actually more interested in STT (ASR) but the choices there are rather limited.

1. odie5533 ◴[03 Sep 25 14:36 UTC] No.45116346[source]▶

Best TTS: VibeVoice, Chatterbox, Dia, Higgs, F5 TTS, Kokoro, Cosy Voice, XTTS-2.

replies(1): >>45124463 #

2. kroaton ◴[04 Sep 25 07:12 UTC] No.45124463[source]▶

Unmute.sh (same team as Kokoro) gets slept on, but it's really good.

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