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

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

[Twilio](https://yomu.fyi/company/twilio) · Paul Kamp · Sep 10, 2026

**Type:** Tutorial

## 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.

## Context

The tutorial addresses outbound callbacks such as appointment reminders and delivery updates, where an AI agent needs to initiate a phone call. It also notes that outbound calling requires permitted numbers, model access, and compliance with applicable regulations, including the TCPA in the United States.

## Approach / What changed

A Node.js application uses Twilio Programmable Voice to place the call and Media Streams to relay audio to GPT-Live-1. Fastify, ws, dotenv, and the Twilio helper library support the server, while a public tunnel exposes it. The agent uses get\_callback\_reason for callback notes and hosted web\_search for factual questions.

## Takeaways

- The destination is supplied with the --call flag and rejected before dialing if it does not match the expected E.164 format.
- The assistant uses get\_callback\_reason for the callback note and OpenAI's hosted web\_search for factual questions.
- The demo requires a Twilio Voice number, an allowed destination, GPT-Live-1 access, Node.js 22 or later, and a publicly reachable server.

**Tags:** [Node.js](https://yomu.fyi/topic/node-js), [OpenAI API](https://yomu.fyi/topic/openai-api), [Twilio](https://yomu.fyi/topic/twilio), [WebSockets](https://yomu.fyi/topic/websockets)

- Source: [Twilio](https://www.twilio.com/en-us/blog/developers/tutorials/integrations/outbound-calls-openai-gpt-live-1-node)
- Source URL: https://www.twilio.com/en-us/blog/developers/tutorials/integrations/outbound-calls-openai-gpt-live-1-node
- Ingested by Yomu: 2026-09-11T04:01:51.364Z

[Read original post](https://www.twilio.com/en-us/blog/developers/tutorials/integrations/outbound-calls-openai-gpt-live-1-node)