Documentation regarding priting text response

Hello guys. I am having a bit of problem in an application i am trying to make. I am using the gpt-3-turbo by using the API key. what i want to do is display/ convert the text response into video while it is generating because for longer responses it takes time and I do not want to first save the string and then convert it into an audio file.
Any ideas how do I execute it. I have read the documentation but I have found no clue so far. any help would be appreciated

Hi @ebadsahab

Welcome to the community.

If you want to receive tokens as they are generated by gpt-3.5-turbo you can stream the responses by setting the stream to true.