OpenAI Audio Models

#1

Post by IndignantTyrant » Thu, Mar 20, 2025, 5:18 PM UTC

Re: OpenAI Audio Models

#2

Post by minimaxir » Thu, Mar 20, 2025, 5:25 PM UTC

This is an official OpenAI tool linked from the new model announcement (https://openai.com/index/introducing-our-next-generation-aud... ), despite the branding difference.

Re: OpenAI Audio Models

#3

Post by danso » Thu, Mar 20, 2025, 5:37 PM UTC

The voices are pretty convincing. It's funny to hear drastically the tone of the reading can change when repeatedly stopping and restarting the samples without changing any of the settings.

Re: OpenAI Audio Models

#4

Post by nickthegreek » Thu, Mar 20, 2025, 5:38 PM UTC

Try the refresh button to get a new list of vibe styles.

Re: OpenAI Audio Models

#5

Post by varunneal » Thu, Mar 20, 2025, 5:38 PM UTC

One of the most novel demos I've seen openai ship in a few years. I love how it looks almost like a synth. Fun to play around with!

Re: OpenAI Audio Models

#6

Post by stephenheron » Thu, Mar 20, 2025, 5:38 PM UTC

Quite disappointing their speech to text models are not open source. Whisper was really good and it was great it was open to play around with. I guess this continues OpenAI's approach of not really being open!

Re: OpenAI Audio Models

#7

Post by Etheryte » Thu, Mar 20, 2025, 5:40 PM UTC

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

#8

Post by nickthegreek » Thu, Mar 20, 2025, 5:40 PM UTC

stephenheron wrote: post #6

Quite disappointing their speech to text models are not open source. Whisper was really good and it was great it was open to play around with. I guess this continues OpenAI's approach of not really being open!

Indeed. Right now I think our open choices are Piper, Kokoro and Orpheus.

Re: OpenAI Audio Models

#9

Post by jcmp » Thu, Mar 20, 2025, 5:45 PM UTC

How do you call this desing/ui astethic? I like it

Re: OpenAI Audio Models

#10

Post by danso » Thu, Mar 20, 2025, 5:45 PM UTC

Interesting, I inserted a bunch of "fuck"s in the text and the "NYC Cabbie" voice read it all just fine. When I switched to other voices ("Connoisseur", "Cheerleader", "Santa"), it responded "I'm sorry I can't assist with that request".

I switched back to "NYC Cabbie" and it again read it just fine. I then reloaded the session completely, refreshed the voice selections until "NYC Cabbie" came up again, and it still read the text without hesitation.

The text:

> In my younger and more vulnerable years my father fuck gave me some fuck fuck advice that I've been fuck fuck FUCK OH FUCK turning over in my mind ever since.

> "Whenever you feel like criticizing any one," he told me, oh fuck! FUCK! "just remember that all the people in this world haven't had fuck fuck fuck FUCKERKER the advantages that you've had."

edit: "Emo Teenager", "Mad Scientist", and "Smooth Jazz" are able to read the text. However, "Medieval Knight" and "Robot" cannot.