News for hackers. Stuff that matters.
Re:OpenAI Audio Models by Etheryte on Thursday March 20, 2025 @01:40PM (#43426324)
Recommended input for anyone trying this out:

Voice: Onyx

Vibe: Heavy german accent, doing an Arnold Schwarzenegger impression, way over the top for comedic effect. Deep booming voice, uses pauses for dramatic effect.

Re:OpenAI Audio Models by rybthrow2 on Thursday March 20, 2025 @03:54PM (#43428096)
This is hilarious, extra points if you get it to say:

"Get to the chopper now and PUT THAT COOKIE DOWN NOWWWW"

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.
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.
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?
Re:OpenAI Audio Models by jeffharris on Thursday March 20, 2025 @01:59PM (#43426636)
Re:OpenAI Audio Models by soared on Thursday March 20, 2025 @03:55PM (#43428108)
Weird 1 in maybe 5 times when I refresh that page I get a very good Arnold. The rest are very bad.
Re:OpenAI Audio Models by Sohcahtoa82 on Thursday March 20, 2025 @04:23PM (#43428449)
I hit Play 3 times and got 3 very different results.

One merely sounded like it had a slight German accent, once just sounded kind of raspy, and the third sound like a normal American English speaker.

Re:OpenAI Audio Models by o_____________o on Thursday March 20, 2025 @02:08PM (#43426774)
interesting to see what accents do and do not work
Re:OpenAI Audio Models by dougiejones on Thursday March 20, 2025 @04:26PM (#43428488)
My recommendation for Ash:

Delivery: Cow noises. You are actually a cow. You can only moo and grunt. No human noises. Only moo. No words.

Pauses: Moo and grunt between sentences. Some burps and farts.

Tone: Cow.

Re:OpenAI Audio Models by istjohn on Friday March 21, 2025 @04:08AM (#43432967)
Hilarious. In addition to lots of moo's and moo-ack's it hallucinated random words and phrases that weren't in the script.