OpenAI Audio Models • Hacker News Board

Re: OpenAI Audio Models

#291

Post by yousif_123123 » Fri, Mar 21, 2025, 2:00 PM UTC

ImprobableTruth wrote: post #280

camillomiller wrote: post #273

Earlier quoted context omitted.

They said themselves that even inference is losing them money tho, or did I get that wrong?

On their subscriptions, specifically the pro subscription, because it's a flatrate to their most expensive model. The API prices are all much more expensive. It's unclear whether they're losing money on the normal subscriptions, but if so, probably not by much. Though it's definitely closer to what you described, subsidizing it to gain 'mindshare' or whatever.

Well I think there's many cheaper models in terms of bang for buck currently per token and intelligence than gpt4o. Other than OpenAI having very high rate limits and throughout available without a contract done with sales, I don't see much reason to use it currently instead of sonnet 3.5 or 3.7, or Google's Flash 2.0

Perhaps their training cost and their current inference cost is higher, but what you get as a customer is a more expensive product for what it is, IMO.

Re: OpenAI Audio Models

#292

Post by fumeux_fume » Fri, Mar 21, 2025, 2:03 PM UTC

These models show some good improvements in allowing users to control many aspects of the delivery, but it falls deep in the uncanny valley and still has a ways to go in not sounding weird or slightly off-putting. I much prefer the current advanced voice models over these.

Re: OpenAI Audio Models

#293

Post by gherard5555 » Fri, Mar 21, 2025, 2:27 PM UTC

I tried some wacky strings like "𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯NNNNNNNNNNNNNN𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯"

Its hilarious either they start to make harsh noise or say nonsense trying so sing something

Re: OpenAI Audio Models

#294

Post by gherard5555 » Fri, Mar 21, 2025, 2:42 PM UTC

gherard5555 wrote: post #293

I tried some wacky strings like "𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯NNNNNNNNNNNNNN𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯𝆺𝅥𝅯�…

Also this one is terrifying if combined with the fitness instructor :

"*scream* AAAAAAAAAAAAAAAAAAAHHHHHHHHHHHHHHHAAAAAAAAAAAAAAAAAAAHHHHHHHHHHHHHHHAAAAAAAAAAAAAAAAAAAHHHHHHHHHHHHHHHAAAAAAAAAAAAAAAAAAAHHHHHHHHHHHHHHHAAAAAAAAAAAAAAAAAAAHHHHHHHHHHHHHHHAAAAAAAAAAAAAAAAAAAHHHHHHHHHHHHHHHAAAAAAAAAAAAAAAAAAAHHHHHHHHHHHHHHHAAAAAAAAAAAAAAAAAAAHHHHHHHHHHHHHHH !!!!!!!!!"

Re: OpenAI Audio Models

#295

Post by rachofsunshine » Fri, Mar 21, 2025, 2:50 PM UTC

Impressive in terms of quality, not so much in terms of style. I tried feeding it two prompts with the same script - one to be straightforward and didactic, then one asking it to deliver calculus like a morning shock-jock DJ. They sounded quite similar, and it definitely did not capture the vibe of 97.3 FM's Altman & the Claude with the latter prompt.

But then, I got much better results from the cowboy prompt by changing "partner" to "pardner" in the text prompt (even on neighboring words). So maybe it's an issue with the script and not the generation? Giving it "pardner" and an explicit instruction to use a Russian accent still gives me a Texas drawl, so it seems like the script overrides the tone instructions.

Re: OpenAI Audio Models

#296

Post by solardev » Fri, Mar 21, 2025, 3:15 PM UTC

KeplerBoy wrote: post #260

solardev wrote: post #87

Earlier quoted context omitted.

Guess that's why the video game voice actors are still on strike: https://en.m.wikipedia.org/wiki/2024%E2%80%93present_SAG-AFT... If we as developers are scared of AI taking our jobs, the voice actors have it much worse...

I don't see how a strike will do anything but accelerate the professions inevitable demise. Can anyone explain how this could ever end in favor of the human laborers striking?

I am not affiliated with the strikers, but I think the idea is that, for now, the companies still want to use at least some human voice acting. So if they want to hire them, they either have to negotiate with the guild or try to find an individual scab willing to cross the picket line and get hired despite the strike. In some industries, there's enough non-union workers that finding replacement workers is easy enough. I guess the voice actors are sufficiently unionized that it's not so easy there, and it seems to have caused some delays in production and also some games being shipped without all their voice lines.

But as you surmise, this is at best a stalling tactic. Once the tech gets good enough, fewer companies will want to pay for human voice acting labor. Unions can help powerless individuals negotiate better through collective bargaining, but they can't altogether stop technological change. Jobs, theirs and ours, eventually become obsolete...

I don't necessarily think we should artificially protect jobs against technology, but I sure wish we had a better social safety net and retraining and placement programs for people needing to change careers due to factors outside their control.

Re: OpenAI Audio Models

#297

Post by goshx » Fri, Mar 21, 2025, 3:22 PM UTC

noahlt wrote: post #254

goshx wrote: post #216

Earlier quoted context omitted.

OpenAI’s Realtime speech to speech is far superior than ElevenLabs.

What ElevenLabs and OpenAI call “speech to speech” are completely different. ElevenLabs’ takes as input audio of speech and maps it to a new speech audio that sounds like a different speaker said it, but with the exact same intonation. OpenAI’s is an end-to-end multimodal conversational model that listens to a user speaking and responds in audio.

I see now. Thank you for clarifying. I thought this about ElevenLabs Conversational API.

Re: OpenAI Audio Models

#298

Post by MasterScrat » Fri, Mar 21, 2025, 3:42 PM UTC

jeffharris wrote: post #18

Hey, I'm Jeff and I was PM for these models at OpenAI. Today we launched three new state-of-the-art audio models. Two speech-to-text models—outperforming Whisper. A new TTS model—you can instruct it how to speak (try it on openai.fm!). And our Agents SDK now supports audio, making it easy to turn text agents into voice agents. We think you'll really like these models. Let me know if you have any questions here!

I think it'd be worth clarifying on the openai.fm website that it's an official OpenAI product. I wasn't sure it was until I saw your comment here.

Re: OpenAI Audio Models

#299

Post by MasterScrat » Fri, Mar 21, 2025, 3:48 PM UTC

Comparing the professionally recorded Baldur's Gate Chapter 2 intro with its AI counterpart:

- Original: https://www.youtube.com/watch?v=FYcMU3_xT-w&t=5s

- AI: https://www.openai.fm/#8e9915b0-771d-4123-8474-78cc39978d33

Re: OpenAI Audio Models

#300

Post by solardev » Fri, Mar 21, 2025, 3:52 PM UTC

d4rkp4ttern wrote: post #279

crazygringo wrote: post #75

This is astonishing. I can type anything I want into the "vibe" box and it does it for the given text. Accents, attitudes, personality types... I'm amazed. The level of intelligent "prosody" here -- the rhythm and intonation, the pauses and personality -- I wasn't expecting anything like this so soon. This is truly remarkable. It understands both the text and the prompt for how the speaker should sound. Like, we're g…

Didn’t look closely, but is there a way to clone a voice from a few seconds of recording and then feed the sample to generate the text in the same voice?

Not here. ElevenLabs can do that.