Hi,
I have been using the gpt-4o-audio-preview and it is working fine, but sometimes for a very small text when I set the temperature to 0.1 it generates a large audio with noise sound. I tried a few times, and I paid more than $30 just for 3-4 time call. I believe there is a bug both for the cost evaluation and for generating voice.
Cheers,
I just saw that it ha sbeen previously reported:
I wanted to flag an issue we encountered while using the gpt-4o-audio-preview model, which led to unexpected costs and might be worth discussing for those using similar setups.
Here’s the situation:
We were running the audio-preview model with the temperature parameter set to 0, which is our default for text models. However, this caused the model to emit continuous noise, rather than silence or a logical halt when there was no audio content. This behavior wasn’t explicitly mentioned in the doc…
Hi,
Attached below is my code reference for the Twilio Realtime API (99% identical to the official Twilio example published last month).
Unfortunately, any temperature lower than 0.6 results in a “white noise” effect that makes the usability impossible. The white noise “replaces” the bot responses.
Has anyone experienced this or knows how to work around it?
import os
import json
import base64
import asyncio
import websockets
from fastapi import FastAPI, WebSocket, Request
from fastapi.respon…