Assistant API - text-to-speech

Hi all,

I am trying to get speech-to-text from the assistant API, dynamically. What I mean is that the output should be constantly talking if the conversation is going. At the moment I only get a single mp3 which I have to play (using Node/Express).

Any tips? :slight_smile:

No tips to offer unfortunately…,but I’m trying to figure this out now. Did you ever end up figuring it out?