Hello,
Lets say I have the transcript of a group discussion between several people as a text file and I want to convert it to audio i.e., re-create the audio experience if you will. How can I do this? I am looking at the text to speech API and the code example provided here.
The issue with this is that my transcript will be like:
Person 1: ...
Person 2: ...
Person 3: ...
If I feed each sentence to the API I will end up with many API calls and many MP3 files that now I have to stitch together. So I am looking for a way to make one (or a few) API calls and get back the result. Further, I want to playback the stream rather than save it as MP3 on disk. How can I do that?
Thanks. I am new to this API and never used it before so apologize if this is a noob question.
LinkedIn
Twitter
