Hey everyone — I'm Arpan, voice AI infrastructure engineer based in India. 28 years shipping production systems. I build the layer most people don't touch — self-hosted LiveKit (not Cloud), SIP trunking, TTS/STT on bare-metal GPUs, telephony routing, failover, the works. When a VAPI project hits cost or scale limits, that's usually where I come in. What's running in production right now: — Enterprise voice system doing 300K+ calls/day, self-hosted telephony with SIP trunk integration — Taxi dispatch: 10K+ daily calls, 99.3% success rate, 75ms address lookups, multi-language — Self-hosted TTS across 10 GPU instances, 1.13M+ clips processed, cut a client's annual cost from $283K to $24K — Real-time video avatar with controllable facial expressions (eyebrows, blinks, pupil movement) for a healthcare deployment I've been running self-hosted LiveKit in production for a while now so happy to share what I've learned about the tradeoffs vs VAPI/Retell, especially around cost, latency, and scaling past the demo stage. Looking forward to the conversations here.

Building voice agents for dental clinics using Retell.ai, n8n & Airtable. Got asked about data privacy during a demo and realized I don't fully understand how to secure the entire flow — especially when integrating with EMRs like Oscar Pro. I know the terms — HIPAA, BAA, TLS, PHI — but I can't fully visualize where patient data is exposed and how to lock it down end to end. This is a real gap for me right now and it's blocking me from moving forward confidently with clinic clients. This is really important to me. I want to do this the right way before I scale. If you've built HIPAA-compliant automations or integrated voice AI into healthcare — please drop a comment, DM me, or even just point me to the right resource. I'm willing to jump on a call too if someone's open to it. Don't let me figure this out the wrong way 🙏 Your input could genuinely change how I build this.