Make Outbound Calls with Twilio Voice and Media Streams, GPT-Live-1 in the OpenAI API, and Node.js

Summary

This tutorial shows how to build an outbound AI voice agent that uses Twilio Programmable Voice and Media Streams to call a permitted phone number, rather than waiting for inbound calls. It connects the call to GPT-Live-1 in the OpenAI API through a Node.js server, with Fastify, ws, dotenv, and the Twilio helper library handling the application and relay. The implementation reads the destination from a --call flag, validates E.164 formatting, exposes the server through a public tunnel, and uses environment variables for credentials and the calling number. Owlie identifies itself as an AI assistant, retrieves a callback note with get_callback_reason, delegates factual questions to hosted web_search, and can be interrupted during speech. The completed demo rings the chosen number, explains why it is calling, and can return random callback notes or web-searched answers, while the tutorial stresses verified numbers, model access, and outbound-calling compliance.

Takeaways

1. 1

   The destination is supplied with the --call flag and rejected before dialing if it does not match the expected E.164 format.

2. 2

   The assistant uses get_callback_reason for the callback note and OpenAI's hosted web_search for factual questions.

3. 3

   The demo requires a Twilio Voice number, an allowed destination, GPT-Live-1 access, Node.js 22 or later, and a publicly reachable server.