# Onboarding

Twilio's Conversation Relay extends voice interactions by integrating real-time speech recognition and synthesis into your applications. You can use this service to create flexible and responsive conversational experiences.

This guide walks you through the process of integrating your Twilio application with the Conversation Relay service.

## Prerequisites

Complete these prerequisite steps before starting the integration process:

### Set up your Twilio account

Ensure you have a Twilio account set up and log into the [Twilio Console](https://www.twilio.com/console).

### Configure WebSocket server

Set up a [WebSocket](/docs/glossary/what-are-websockets) server to handle communication with Conversation Relay.

You can set up a WebSocket server using various frameworks and programming languages, such as [Node.js with Fastify](https://github.com/robinske/cr-demo/blob/main/server.js), [Python with FastAPI](https://github.com/rishabkumar7/cr-demo-python/blob/main/main.py), or others that support WebSocket protocols.

**Note**: Ensure your WebSocket server is accessible via a `wss://` URL.

#### WebSocket security with signature validation

Conversation Relay includes an `X-Twilio-Signature` header in the initial WebSocket handshake request. This signature allows you to validate that requests are genuinely coming from Twilio, following the same verification mechanism used for standard Twilio webhooks.

To validate this signature:

1. Extract the `X-Twilio-Signature` header from the incoming WebSocket connection request.
2. Use your Twilio auth token and the request URL to validate this signature.
3. Only accept connections with valid signatures to prevent spoofed requests.

For detailed implementation guidance, refer to [Twilio's webhook security documentation](/docs/usage/webhooks/webhooks-security).

## Integrate Twilio with Conversation Relay

Once you've completed the prerequisites, follow these steps to integrate your Twilio application with Conversation Relay.

### Configuration steps in the Twilio Console

1. Log in to your [Twilio Console](https://www.twilio.com/console).
2. Navigate to the **Voice** section, select **General** under **Settings**, and turn on the **Predictive and Generative AI/ML Features Addendum** in order to use Conversation Relay.
3. Navigate to the **Voice** section and select **TwiML Apps** under **Manage**.
4. Create a new TwiML App or select an existing one.
5. In the TwiML App settings, configure the Voice URL to point to your application's endpoint (for example, `https://yourserver.com/voice`) where Twilio can retrieve the TwiML containing the `<ConversationRelay>` instructions.
6. Save your changes.

### Configure Conversation Relay in your application

> \[!WARNING]
>
> Ensure your WebSocket server is properly configured to handle incoming messages from Conversation Relay. If not, you may encounter connection errors.

After configuring your TwiML App, update your application to handle Conversation Relay interactions:

* Use the [`<Connect><ConversationRelay>` TwiML noun](/docs/voice/twiml/connect/conversationrelay) to route calls to the [Conversation Relay service](/docs/voice/twiml/connect/conversationrelay).
* Specify the WebSocket URL and any [additional attributes](/docs/voice/twiml/connect/conversationrelay#conversationrelay-attributes) needed for your use case.

Example TwiML:

```xml
<?xml version="1.0" encoding="UTF-8"?>
<Response>
  <Connect action="https://myhttpserver.com/connect_action">
    <ConversationRelay url="wss://mywebsocketserver.com/websocket" welcomeGreeting="Hi! Ask me anything!" />
  </Connect>
</Response>
```

## Develop your application with Conversation Relay

Once you've integrated Conversation Relay, you can enhance your application with advanced voice capabilities. Consider the following features:

### Real-time speech recognition

Use Conversation Relay's real-time speech recognition to process caller input and respond dynamically.

### Text-to-speech synthesis

Use Conversation Relay to convert text responses into natural-sounding speech, providing a seamless conversational experience.

For optimal speech quality, apply proper text normalization techniques (such as writing out numbers as words or spelling out abbreviations). See the [Conversation Relay documentation](/docs/voice/twiml/connect/conversationrelay#text-normalization-best-practices) for detailed text normalization best practices.

### Custom parameters

Pass [custom parameters](/docs/voice/twiml/connect/conversationrelay#parameter-element) to Conversation Relay to tailor interactions based on specific use cases.

## Next steps

Learn more about building applications with Conversation Relay by exploring the following tutorials:

* [Integrate OpenAI with Twilio Voice Using Conversation Relay](https://twilio.com/en-us/blog/integrate-openai-twilio-voice-using-conversationrelay)
* [Building Voice Bots with Twilio's Conversation Relay](https://twilio.com/en-us/blog/voice-ai-build-voice-bots-conversation-relay)
* [Conversation Relay Application and Architecture for Voice AI Applications Built on AWS](https://twilio.com/en-us/blog/conversation-relay-aws-reference-architecture)