News for hackers. Stuff that matters.

A comment on OpenAI Audio Models. Parent comment

Re:OpenAI Audio Models by mft_ on Thursday March 20, 2025 @02:19PM (#43426927)
Weird; trying exactly this, and every time I stop and play again, I get a totally different voice. One of them (if I'm not mistaken) was cod-Russian.
[ Parent | on HN ]
Re:OpenAI Audio Models by Etheryte on Thursday March 20, 2025 @03:34PM (#43427858)
Yeah, that's both odd and very unfortunate, it seems incredibly nondeterministic. Even running this with the same exact parameters over and over gives widely different results.
[ Parent | on HN ]
Re:OpenAI Audio Models by mchusma on Thursday March 20, 2025 @03:17PM (#43427687)
I also find this strange, and I wonder if I can get a consistent voice out of this. If using the api with a vibe/instructions for a back and forth, will it be consistent? This example app they provide implies no?
[ Parent | on HN ]