October 28, 2026
Written by
Reviewed by
Twilio’s Conversation Relay allows you to build real-time, human-like voice applications with AI Large Language Models (LLMs) that you can call using Twilio Voice. Conversation Relay connects to a WebSocket you control, allowing you to integrate the LLM provider of your choice over a fast two-way connection.
This tutorial demonstrates a basic integration of Claude, Anthropic's AI model, with Twilio Voice using Conversation Relay. By the end of this guide, you'll have a functioning Claude voice assistant powered by a Node.js server that lets you call a Twilio phone number and engage in conversation with an Anthropic model!
Prerequisites
To deploy this tutorial, you'll need:
- Node.js 24+ (I used 24.22.0 to build this tutorial)
24+ (I used 24.22.0 to build this tutorial)
- A Twilio account (you can sign up for free, here) and a phone number with voice capabilities
A Twilio account (you can sign up for free, here) and a phone number with voice capabilities
An Anthropic account and API Key
- Ngrok or another tunneling solution to expose your local server to the internet for testing
or another tunneling solution to expose your local server to the internet for testing
- A phone to place your outgoing call to Twilio
A phone to place your outgoing call to Twilio
- Your code editor or IDE of choice
Your code editor or IDE of choice
Before using Conversation Relay, you need to complete the onboarding steps and if you agree to the Predictive and Generative AI/ML Features Addendum, agree there. In the Twilio Console, go to Communications > Voice > Settings > Privacy & Security. See the Conversation Relay Onboarding Guide for more details.
Great! Let’s get started.
Set up your project
These next steps will cover project setup and the dependencies you’ll need to install. Then, you'll create the server code (and I’ll explain the more interesting parts).
Create the project directory
First, set up a new project folder:
Copy code
Initialize the Node.js Project
Next, initialize a new Node.js project and install the necessary packages:
Copy code
You'll be using Fastify to create a server that handles both the WebSocket needed for Conversation Relay and the endpoint for Twilio instructions required by Twilio Voice. You’ll use Anthropic’s Typescript library to manage the conversation with Claude.
Configure Environment Variables
Create an .env file to store your Anthropic API key. Add the following line:
Copy code
If you are working with git, add .env to a .gitignore file to prevent exposing sensitive information.
Write the code
Awesome, you’re really cooking now. Let’s move on to the server code.
Create a file named server.js and add the following imports and constants:
Copy code
Here, you’ll notice we define our WELCOME_GREETING. This is the first thing someone will hear when they dial into your assistant.
You’ll also notice a SYSTEM_PROMPT, which controls the behavior of the voice assistant. There, we let the LLM know some of our preferences for the conversation. This prompt asks the LLM to avoid special characters and asks it to write out numbers to make it easier for the Text-to-Speech step to work.
Implement the AI response function
In this next step, you will define how your app connects to the Anthropic API and handle responses. Paste this code below the above:
Copy code
Here, you add what we need to connect to Anthropic. process.env.ANTHROPIC_API_KEY will get our API key from the .env file to authenticate our usage of Anthropic, then the aiResponse function is what is used to control the behavior of each LLM response.
For this demo, you will use claude-sonnet-5-5 at low effort to test the build. You can find Anthropic’s supported Claude models in their documentation.
We tested this tutorial with both Claude Sonnet 5.5 and Claude Haiku 5.5, and both handled real-time voice well at low effort. We use Sonnet 5.5 in the code, but the right choice depends on your use case. Anthropic’s model comparison table and guide to choosing a model are good places to start.
Configure Fastify, and set up routes
Now that you've defined your interactions with Claude, it's time to move on to Twilio. You're going to set up two endpoints in this step:
- /twiml - to control Twilio’s behavior when we make an incoming call to our purchased number. This uses Twilio Markup Language, or TwiML, to instruct Twilio further.
- /ws - for a WebSocket connection that Conversation Relay will use to communicate with your application. Here you will receive messages from Twilio, but you will also need to pass messages from your LLM back to Twilio to trigger the Text-to-Speech step (the relay, if you will).
Below the code from the above step, paste the following:
Copy code
And that’s all the code you need for a basic integration – now, let’s get everything running and connect it to Twilio!
Start ngrok and the server
Open a terminal (or a new terminal tab) and start ngrok with ngrok http 8080.
There, copy the ngrok URL without the scheme (that is, leave out the “https://” or “http://”) and update your .env file by adding a new line:
Copy code
This screenshot shows the URL I chose for my environment variable:
Finally, start your server. In the original terminal (not the one running ngrok), run:
Copy code
Configure Twilio
In theTwilio Console, configure your phone number with the Voice Configuration Webhook for A call comes in set to https://[your-ngrok-subdomain].ngrok.app/twiml.
Here’s an example from my Console:
Save your changes, you’re now ready to test.
Test your integration
Are you giddy with anticipation? It’s time!
Call your Twilio number. The AI should greet you with the WELCOME_MESSAGE and be ready for a conversation – be sure to ask it for owl jokes!
Next steps with Twilio and Claude
I hope you enjoyed this basic integration of Twilio Voice with Anthropic’s Claude using Conversation Relay – dial-a-voice-LLM in under 100 lines of code!
You’ll probably want to add more advanced features next. Our follow-up article shows you how to stream tokens from Anthropic to Conversation Relay to reduce latency, as well as how to better handle interruptions by tracking your conversation locally. And after that, I’ll show you the basics of how to call tools or functions with Claude using Conversation Relay.
But until then, have fun with the scaffolding… check out Twilio’s Conversation Relay docs, Anthropic’s API documentation, and Anthropic’s TypeScript SDK to learn more.
Paul Kamp is the Technical Editor-in-Chief of the Twilio Blog. He was excited to talk to the LLM about recipes… but a bit disappointed he only found time to cook a few suggestions (when will agents make food?). Reach Paul at pkamp [at] twilio.com.
