Vite (Javascript) | ElevenLabs Documentation

This tutorial will guide you through creating a web client that can interact with a ElevenLabs agent. You’ll learn how to implement real-time voice conversations, allowing users to speak with an AI agent that can listen, understand, and respond naturally using voice synthesis.

Looking to build with React/Next.js? Check out our Next.js guide

What You’ll Need

An ElevenLabs agent created following this guide
npm installed on your local system
Basic knowledge of JavaScript

Project Setup

Create a Project Directory

Open a terminal and create a new directory for your project:

mkdir elevenlabs-conversational-ai
cd elevenlabs-conversational-ai

Initialize npm and Install Dependencies

Initialize a new npm project and install the required packages:

npm init -y
npm install vite @elevenlabs/client

Set up Basic Project Structure

Add this to your package.json:

package.json

{
    "scripts": {
        ...
        "dev:frontend": "vite"
    }
}

Create the following file structure:

elevenlabs-conversational-ai/
├── index.html
├── script.js
├── package-lock.json
├── package.json
└── node_modules

Implementing the Voice Chat Interface

Create the HTML Interface

In index.html, set up a simple user interface:

index.html

<!DOCTYPE html>
<html lang="en">
    <head>
        <meta charset="UTF-8" />
        <meta name="viewport" content="width=device-width, initial-scale=1.0" />
        <title>ElevenLabs Agents</title>
    </head>
    <body style="font-family: Arial, sans-serif; text-align: center; padding: 50px;">
        <h1>ElevenLabs Agents</h1>
        <div style="margin-bottom: 20px;">
            <button id="startButton" style="padding: 10px 20px; margin: 5px;">Start Conversation</button>
            <button id="stopButton" style="padding: 10px 20px; margin: 5px;" disabled>Stop Conversation</button>
        </div>
        <div style="font-size: 18px;">
            <p>Status: <span id="connectionStatus">Disconnected</span></p>
            <p>Agent is <span id="agentStatus">listening</span></p>
        </div>
        <script type="module" src="../images/script.js"></script>
    </body>
</html>

Implement the Conversation Logic

In script.js, implement the functionality:

script.js

import { Conversation } from '@elevenlabs/client';
const startButton = document.getElementById('startButton');
const stopButton = document.getElementById('stopButton');
const connectionStatus = document.getElementById('connectionStatus');
const agentStatus = document.getElementById('agentStatus');
let conversation;
async function startConversation() {
    try {
        // Request microphone permission
        await navigator.mediaDevices.getUserMedia({ audio: true });
        // Start the conversation
        conversation = await Conversation.startSession({
            agentId: 'YOUR_AGENT_ID', // Replace with your agent ID
            onConnect: () => {
                connectionStatus.textContent = 'Connected';
                startButton.disabled = true;
                stopButton.disabled = false;
            },
            onDisconnect: () => {
                connectionStatus.textContent = 'Disconnected';
                startButton.disabled = false;
                stopButton.disabled = true;
            },
            onError: (error) => {
                console.error('Error:', error);
            },
            onModeChange: (mode) => {
                agentStatus.textContent = mode.mode === 'speaking' ? 'speaking' : 'listening';
            },
        });
    } catch (error) {
        console.error('Failed to start conversation:', error);
    }
}
async function stopConversation() {
    if (conversation) {
        await conversation.endSession();
        conversation = null;
    }
}
startButton.addEventListener('click', startConversation);
stopButton.addEventListener('click', stopConversation);

Start the frontend server

npm run dev:frontend

Make sure to replace 'YOUR_AGENT_ID' with your actual agent ID from ElevenLabs.

(Optional) Authenticate with a Signed URL

This authentication step is only required for private agents. If you’re using a public agent, you can skip this section and directly use the agentId in the startSession call.

Create Environment Variables

Create a .env file in your project root:

.env

ELEVENLABS_API_KEY=your-api-key-here
AGENT_ID=your-agent-id-here

Make sure to add .env to your .gitignore file to prevent accidentally committing sensitive credentials.

Setup the Backend

Install additional dependencies:

npm install express cors dotenv

Create a new folder called backend:

elevenlabs-conversational-ai/
├── backend
...

Create the Server

backend/server.js

require("dotenv").config();
const express = require("express");
const cors = require("cors");
const app = express();
app.use(cors());
app.use(express.json());
const PORT = process.env.PORT || 3001;
app.get("/api/get-signed-url", async (req, res) => {
    try {
        const response = await fetch(
            `https://api.elevenlabs.io/v1/convai/conversation/get-signed-url?agent_id=${process.env.AGENT_ID}`,
            {
                headers: {
                    "xi-api-key": process.env.ELEVENLABS_API_KEY,
                },
            }
        );
        if (!response.ok) {
            throw new Error("Failed to get signed URL");
        }
        const data = await response.json();
        res.json({ signedUrl: data.signed_url });
    } catch (error) {
        console.error("Error:", error);
        res.status(500).json({ error: "Failed to generate signed URL" });
    }
});
app.listen(PORT, () => {
    console.log(`Server running on http://localhost:${PORT}`);
});

Update the Client Code

Modify your script.js to fetch and use the signed URL:

script.js

// ... existing imports and variables ...
async function getSignedUrl() {
    const response = await fetch('http://localhost:3001/api/get-signed-url');
    if (!response.ok) {
        throw new Error(`Failed to get signed url: ${response.statusText}`);
    }
    const { signedUrl } = await response.json();
    return signedUrl;
}
async function startConversation() {
    try {
        await navigator.mediaDevices.getUserMedia({ audio: true });
        const signedUrl = await getSignedUrl();
        conversation = await Conversation.startSession({
            signedUrl,
            // agentId has been removed...
            onConnect: () => {
                connectionStatus.textContent = 'Connected';
                startButton.disabled = true;
                stopButton.disabled = false;
            },
            onDisconnect: () => {
                connectionStatus.textContent = 'Disconnected';
                startButton.disabled = false;
                stopButton.disabled = true;
            },
            onError: (error) => {
                console.error('Error:', error);
            },
            onModeChange: (mode) => {
                agentStatus.textContent = mode.mode === 'speaking' ? 'speaking' : 'listening';
            },
        });
    } catch (error) {
        console.error('Failed to start conversation:', error);
    }
}
// ... rest of the code ...

Signed URLs expire after a short period. However, any conversations initiated before expiration will continue uninterrupted. In a production environment, implement proper error handling and URL refresh logic for starting new conversations.

Update the package.json

package.json

{
    "scripts": {
        ...
        "dev:backend": "node backend/server.js",
        "dev": "npm run dev:frontend & npm run dev:backend"
    }
}

Run the Application

Start the application with:

npm run dev

Next Steps

Now that you have a basic implementation, you can:

Add visual feedback for voice activity
Implement error handling and retry logic
Add a chat history display
Customize the UI to match your brand

For more advanced features and customization options, check out the @elevenlabs/client package.