Hey folks 👋 My Startup is Running a Voice AI setup on a single EC2 (c7i.4xlarge – 16 vCPU, 32GB) with LiveKit + FastAPI + Twilio + STT→LLM→TTS + Redis. Trying to hit 50+ concurrent calls, but it starts failing around 10–25 calls. Looking for advice on: • Best way to scale this on AWS (ECS / EKS / multi-node?) ( we need to save cost also) • How to scale LiveKit + real-time pipelines properly • Any known bottlenecks in this kind of setup Would really appreciate any pointers

I’d recommend going with Hostinger VPS. We initially faced issues with AWS, mainly around resource scaling and setup complexity, which is why we shifted to Hostinger VPS. We’ve been using their KVM 8 plan, and it’s been performing very well for us.

Thanks for sharing 🙌 We actually moved from VPS only (KVM 8) to AWS mainly for autoscaling + load balancing. Right now the issue seems less about provider and more about single-node architecture limits, especially with real-time pipelines (LiveKit + STT/LLM/TTS). Trying to figure out the right way to scale