gokuljs

Blog: https://gokuljs.com/blogs/when-latency-becomes-audible code: https://github.com/gokuljs/GoSFU

So when you're building a real-time voice system, there are a lot of hard parts that need to be handled, like voice resampling, jitter buffers, and frame pacing. This blog shows you the mental model of what happens…

I'm open-sourcing GoSFU today. I built it because I wanted a voice agent server I could read, run, and change myself. A voice agent is not just speech-to-text, an LLM, and text-to-speech. That explains how the models…

We say systems are “distributed”, but rarely ask how they stay consistent. What happens when nodes disagree, fail, or lag behind? This post breaks down consensus using Raft into a simple mental model.…

I’ve been a backend-heavy engineer for about 4 to 5 years, mostly in startups. For about 3 months I’ve been reading and building small things, but I’m not sure if I’m progressing or just spinning. I also don’t really…

I’m trying to get an honest perspective on how hiring managers evaluate candidates with startup heavy experience and short tenures. I have ~4.5 years of experience as a software engineer, mostly in early-stage startups.…

Blog: https://gokuljs.com/blogs/retrieval-from-first-principles

Blog: https://gokuljs.com/blogs/retrieval-from-first-principles

I’ve been working on real time voice agents and put together a write up of what I’ve learned about the full stack including WebRTC media transport, streaming STT, incremental LLM inference, and TTS, along with where…