Can we use sockets to receive phone calls (media stream) and transcribe realtime ?

I wanted to build an app which will receive phone calls as a media stream from twilio/plivo.

Not really sure what is the best way to do it.

Twilio sends a media stream .

Can the new sockets capture that and transcribe realtime ? (for transcription we can use external apis)

The problem is .. all this is happening realtime.

Wanted to know if we can do this in xano.

If anyone can point me in right direction , that would be awesome

3 replies