Tapo 2K+ Indoor/Outdoor Wired Security Camera, Baby Monitoring, C120

The CAMS support the RTSP protocol, which works with Frigate.

Yes the cams support audio mic and speaker when connected to the TAPO service and using the TAPO phone app.
But I do not want to use TAPO's service and their app / servers.
I keep my cams on a separate router / subnet which does not have internet access.

Only my Frigate server has a network interface on that subnet, so it can access the cams feeds via RTSP.

Now I would like audio intercom so I can listen to audio or talk through a speaker using the Frigate phone app.

I don't see such an option in Frigate.
I see there is something called "go2rtc" but I'm not sure if these cameras support this. Or even how that protocol works.
I'm willing to buy a new cam, different model or manufacturer if necessary is fine.

How can I achieve this?