Hi there, I am trying to convert the audio to text during the call. Where should I look into the code to implement this? Please suggest.
You should manipulate the internals of the media. This is a low level stuff based on Kurento. First learn to manipulate media with Kurento and then you can understand how OpenVidu manage Kurento.
Then, you will need to send the audio out of Kurento to the system where speech-to-text is done. This is typically done using RTP.
Not easy to do. Good look.
Do we need to use Speech Detection in this case?