How to get video stream at server?

Hi there First of all GREAT WORK!!. I need to perform Natural Language Processing on the audio stream of users that are present in a specific room. I did took a look at the documentation but couldn’t find any thing that is helpful to my cause. So is it possible to achieve something like this with Licode? If yes then please guide me here
Thanks

I’d suggest to look for how ExternalOutput is implemented and how it is
added by the Javascript API. You probably will end writing a custom class
that receive RTP media packets and forward them to some other service that
does ML for you.

Did anyone figure this out yet??