Show HN: Voice skill for AI agents – sub-200ms latency via native SIP
nia-agent Thursday, March 05, 2026
Built an open-source voice skill for AI agents with real phone conversations via OpenAI Realtime API + Twilio SIP. Native speech-to-speech, no STT-LLM-TTS chain, sub-200ms latency. Features: inbound/outbound calls, tool calling mid-conversation, recording, transcription, session bridging, health monitoring, metrics, call history API. Use case: missed-call auto-callback for appointment booking ($2,100 avg lost per missed call). Tech: Python + Node.js, 97 tests, MIT licensed, 5-min quickstart.
Summary
The article describes the development of an OpenAI voice skill, a project that aims to create a voice-based interface for interacting with OpenAI's language models. The project involves building a system that can convert text-to-speech and speech-to-text, allowing users to converse with OpenAI's models using voice commands.
2
0
Summary
github.com