←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: 0s | source
Show context
baxuz ◴[03 Sep 25 12:53 UTC] No.45115119[source]▶
Looking forward to the day when tts and speech recognition will work on Croatian, or other less prevalent languages.

It seems that it's only variants of English, Spanish and Chinese which are somewhat working.

replies(1): >>45115998 #
lukax ◴[03 Sep 25 14:07 UTC] No.45115998[source]▶
Have you tried Soniox for speech recognition? It supports Croatian. Or are you just looking for self-hosted open-source models? Soniox is very cheap ($0.1/h for async, $0.12/h for real-time) and you get $200 free credits on signup.

https://soniox.com/

Disclaimer: I used to work for Soniox

replies(1): >>45117606 #
1. baxuz ◴[03 Sep 25 16:23 UTC] No.45117606[source]▶
I meant in general purpose tools from Google and Apple. Most of this assistant and "AI" stuff is practically useless for me because I refuse to talk to my devices in English.

In Android Auto / CarPlay I can't even get voice guidance that works properly, much less reading notifications, or composing a reply using STT