Most likely in this Summer 2026.

> Im hitting some weird latency issues when I try to push it with real-time video processing Yeah, I had high hopes for the cloud stuff but honestly it was a letdown for my little home project. The lag was just bad. Unfortunately, switching to a NVIDIA GeForce RTX 4070 Super 12GB for local inference ended up being way faster than any API I tried. Cloud just isnt there yet for real-time speed imo.

Late to the party but this whole thread is 💯. Glad I found it.

Ok adding this to my list of things to try. Thanks for the tip!