---
title: "Build an AI Voice Assistant with Twilio Voice and Media Streams, OpenAI's GPT-Live API, and Node.js"
description: "This tutorial shows how to build an AI voice assistant that answers phone calls using Twilio Programmable Voice, Twilio Media Streams, OpenAI's GPT-Live-1, and Node.js. GPT-Live-1 acts as the speech-to-speech model for listening, talking, and handling interruptions, while the delegated gpt-5.6-terra model handles deeper reasoning and tool use. The implementation uses a Fastify server with WebSocket support, dotenv configuration, a marin voice, and separate prompts for the voice and backend roles. Callers can request a city's top headline through the custom get_top_headline function or ask factual questions through OpenAI's hosted web_search tool. The guide exposes port 5050 with ngrok, points a Twilio number at an /incoming-call webhook, and concludes that the working example fits in under 200 lines."
---

# Build an AI Voice Assistant with Twilio Voice and Media Streams, OpenAI's GPT-Live 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 AI voice assistant that answers phone calls using Twilio Programmable Voice, Twilio Media Streams, OpenAI's GPT-Live-1, and Node.js. GPT-Live-1 acts as the speech-to-speech model for listening, talking, and handling interruptions, while the delegated gpt-5.6-terra model handles deeper reasoning and tool use. The implementation uses a Fastify server with WebSocket support, dotenv configuration, a marin voice, and separate prompts for the voice and backend roles. Callers can request a city's top headline through the custom get\_top\_headline function or ask factual questions through OpenAI's hosted web\_search tool. The guide exposes port 5050 with ngrok, points a Twilio number at an /incoming-call webhook, and concludes that the working example fits in under 200 lines.

## Context

The tutorial is motivated by the launch of GPT-Live-1 and presents a way to make its speech-to-speech capabilities available through a phone call. It requires Twilio Voice access, GPT-Live-1 and gpt-5.6-terra API access, Node.js 22 or later, a public tunnel such as ngrok, and a phone for testing.

## Approach / What changed

The implementation combines Twilio Programmable Voice and Media Streams with a Node.js Fastify server, WebSocket support, dotenv, and OpenAI's GPT-Live API. GPT-Live-1 handles the live voice interaction, while gpt-5.6-terra is delegated deeper reasoning and tool use. The assistant uses separate prompts, OpenAI's hosted web\_search tool, and a custom get\_top\_headline function.

## Takeaways

- GPT-Live-1 handles audio interaction and interruptions, while gpt-5.6-terra is used for deeper reasoning and tool calls through delegation.
- The example exposes a Node.js server on port 5050, uses ngrok to make it public, and configures a Twilio voice number to call the /incoming-call webhook.
- The assistant supports both OpenAI's hosted web\_search tool and a custom get\_top\_headline function that accepts a city parameter.

**Tags:** [GPT-Live](https://yomu.fyi/topic/gpt-live), [Node.js](https://yomu.fyi/topic/node-js), [Twilio](https://yomu.fyi/topic/twilio), [WebSockets](https://yomu.fyi/topic/websockets)

- Source: [Twilio](https://www.twilio.com/en-us/blog/developers/tutorials/integrations/voice-ai-assistant-openai-gpt-live-1-node)
- Source URL: https://www.twilio.com/en-us/blog/developers/tutorials/integrations/voice-ai-assistant-openai-gpt-live-1-node
- Ingested by Yomu: 2026-09-11T04:02:06.017Z

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