Add text-to-speech from Assistant API

Hi there,

Does anyone have experience using text-to-speech and the assistant API? And make it dynamic? At the moment I only managed to get a single MP3 file, but what I want is to keep sending the speech to the user which is the same as the text output of the API.

I did it here, you can review the code in the repository:

1 Like

Specifically in this file:

You can see it in action here: (308) Whisper to ChatGPT and Claude.ai (voice interaction with chat) - YouTube

Thanks man! @amve will try it out

2 Likes