Minimizing Latency in LiveKit Voice AI Agents
From Cloud Mesh to Streaming STT/TTS: Techniques for Sub-1.5s End-to-End Latency
7/29/2025
17
6
This blog explores strategies to cut voice agent latency down to under 1.5 seconds using LiveKit, region pinning, preemptive pipelines, and low-latency media configs.
Read More
17 5
Keeping Your Django Server Alive on AWS Even After You Log Out
A Practical Guide to nohup, screen, and Gunicorn Deployment
7/26/2025
7
1
In this blog, I walk you through why your Django server dies when you close the AWS terminal and how to keep it alive using screen.
Read More
13 0