getting realtime audio stream from voip or sip systems

Question

I am building an application that gets real-time audio from our organization's VoIP system, records the call and transcribe the real-time voice. The transcription then passed to our analytics engine and get the insights.

We are able to transcribe the recorded audio and get the insights from the transcription. We have a solution for real-time transcription also. It will transcribe the voice from the microphone and even an RTSP stream also. We are having trouble finding a solution for getting the real-time audio from SIP/VoIP systems. I read that SIP Trunking and option and also WebRTC is also another option. But I don't know how to and where to start with.

I am experienced in Java and Python, I requesting experts to give me suggestions or examples on how to get the real-time audio stream from a SIP/VoIP conversation.

I am not familiar with SIP/VoIP and never written VoIP application.

Answer 1

A solution that might suit your needs is Oreka, which is the open source version of Orecx, a call recording software for VoIP.

I used it in the past and it works perfectly well with SIP calls that use open audio codecs like g711 (alaw,ulaw) or speex but it may have problems decoding the audio of calls that use the propietary g729 codec (I had to work out my own codecs at that time).

The paid version might support more codecs and protocols like Avaya's H323.

Have in mind that this app works by sniffing the network, so the setup is not trivial. Anyway, I suggest you give it a try.

Link: https://www.orecx.com/open-source/