Realtime API extremely expensive

[stevenic]

@Diet

I don’t know if you get charged for unspoken (interrupted), generated speech

I dug into that… My findings here:

Realtime API Details (Costs, Usage, etc.)

Here’s some other costs tests around interruption… I first created a new project and asked the model to count to 100. I then interrupted it by saying stop. I noticed that it had streamed 1 - 38 back to the client but it only had spoken 1 - 5 when I said stop. [image] Next I created a new project and asked the model to count to 100 again. It tried to first count by 10’s so I interrupted that with “no by 1’s”. This time I let it generate the full 100 numbers but I stopped it manually using th…