Why don't we just use Zoom? It's pretty simple. You fire it up. Everyone logs in and they have it in front of them. For translation all you need is a translator whom all those seeking translation can call. The participants have their screens in front of them for the Zoom and they have their phone by their ear for the translation. It's really simple.
The technology is there. There's a small subscription fee. You can probably get it for a couple of hundred bucks a month. I look at the screen and I see who is speaking. I have an earpiece in my ear, and I call the translation line so the translator tells me what the person is saying in the other language.