Full application

Build a web application that uses the Anam SDK’s advanced features. This guide walks you through creating an interactive AI assistant with modern UI components, real-time event handling, chat history, talk commands, and production-grade security practices.

How to use this guide

This guide takes an additive approach, covering a range of Anam features and implementation patterns. Each section builds upon the previous ones, allowing you to add functionality progressively.

We provide detailed, complete code examples to make integration with AI coding assistants straightforward. Use the buttons in the top-right corner of this page to open the content in your preferred LLM or copy the entire guide for easy reference.

You likely won’t need every component shown in this guide. After completing the initial setup (Steps 1-4), use the right-hand navigation to jump directly to the specific features you want to implement.

Start with the basic setup, then selectively add the advanced features that match your use case.

What You’ll Build

By the end of this guide, you’ll have a persona application featuring:

Modern UI/UX with loading states, connection status, and responsive design
Chat History Panel showing conversation transcripts in real-time
Advanced Event Handling for connection management and user feedback
Talk Commands for programmatic persona control
Audio Management with mute/unmute functionality
Production Security with proper authentication and rate limiting
Error Handling & Retry Logic for better user experience

Prerequisites

Node.js (version 18 or higher) and npm installed
Understanding of modern JavaScript/TypeScript
An Anam API key (get one here)
Basic knowledge of Express.js and modern web development
A microphone and speakers for voice interaction

Basic App

If you’ve already completed the Basic Application guide, you can skip to Listening to events. The setup below is similar but included here for completeness.

Let’s start by building a simple working version, then enhance it with advanced features. This foundational setup creates a minimal web application with three main files:

anam-production-app/
├── server.js          # Express server for secure API key handling
├── package.json       # Node.js dependencies
├── public/            # Static files served to the browser
│   ├── index.html     # Main HTML page with video element
│   └── script.js      # Client-side JavaScript for persona control
└── .env               # Environment variables

Create project directory

mkdir anam-production-app
cd anam-production-app

Initialize Node.js project

bash npm init -y This creates a package.json file for managing dependencies.

Create public directory

bash mkdir public

The public folder will contain your HTML and JavaScript files that are served to the browser.

Install dependencies

bash npm install express dotenv

We’re installing Express for the server and dotenv for environment variable management. The Anam SDK will be loaded directly from a CDN in the browser.

Configure environment variables

Create a .env file in your project root to store your API key securely:

.env

ANAM_API_KEY=your-api-key-here

Replace your-api-key-here with your actual Anam API key. Never commit this file to version control.

Step 1: Set up your server

Create a basic Express server to handle session token generation:

server.js

require("dotenv").config();
const express = require("express");
const app = express();

app.use(express.json());
app.use(express.static("public"));

app.post("/api/session-token", async (req, res) => {
  try {
    const response = await fetch("https://api.anam.ai/v1/auth/session-token", {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Authorization: `Bearer ${process.env.ANAM_API_KEY}`,
      },
      body: JSON.stringify({
        personaConfig: {
          name: "Cara",
          avatarId: "30fa96d0-26c4-4e55-94a0-517025942e18",
          avatarModel: "cara-4",
          voiceId: "6bfbe25a-979d-40f3-a92b-5394170af54b",
          llmId: "a7cf662c-2ace-4de1-a21e-ef0fbf144bb7",
          systemPrompt:
            "You are Cara, a helpful AI assistant. Be friendly, concise, and helpful in your responses.",
        },
      }),
    });

    const data = await response.json();
    res.json({ sessionToken: data.sessionToken });
  } catch (error) {
    res.status(500).json({ error: "Failed to create session" });
  }
});

app.listen(8000, () => {
  console.log("Server running on http://localhost:8000");
});

Step 2: Set up your HTML

Create a simple HTML page with a video element and basic controls:

public/index.html

<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>Anam AI Assistant - Production App</title>
  </head>
  <body>
    <div style="text-align: center; padding: 20px;">
      <h1>Chat with Cara</h1>
      <video
        id="persona-video"
        autoplay
        playsinline
        style="max-width: 100%; border-radius: 8px;"
      ></video>
      <div style="margin-top: 20px;">
        <button id="start-button">Start Chat</button>
        <button id="stop-button" disabled>Stop Chat</button>
      </div>
    </div>
    <script type="module" src="script.js"></script>
  </body>
</html>

Step 3: Initialize the Anam client

Create the client-side JavaScript to control your persona:

public/script.js

import { createClient } from "https://esm.sh/@anam-ai/js-sdk@latest";

let anamClient = null;

// Get DOM elements
const startButton = document.getElementById("start-button");
const stopButton = document.getElementById("stop-button");
const videoElement = document.getElementById("persona-video");

async function startChat() {
  try {
    startButton.disabled = true;

    // Get session token from your server
    const response = await fetch("/api/session-token", {
      method: "POST",
    });
    const { sessionToken } = await response.json();

    // Create the Anam client
    anamClient = createClient(sessionToken);

    // Start streaming to the video element
    await anamClient.streamToVideoElement("persona-video");

    // Update button states
    startButton.disabled = true;
    stopButton.disabled = false;

    console.log("Chat started successfully!");
  } catch (error) {
    console.error("Failed to start chat:", error);
    startButton.disabled = false;
  }
}

function stopChat() {
  if (anamClient) {
    // Disconnect the client
    anamClient.stopStreaming();
    anamClient = null;

    // Clear video element
    videoElement.srcObject = null;

    // Update button states
    startButton.disabled = false;
    stopButton.disabled = true;

    console.log("Chat stopped.");
  }
}

// Add event listeners
startButton.addEventListener("click", startChat);
stopButton.addEventListener("click", stopChat);

Step 4: Test your basic setup

Start your server:

node server.js

Open http://localhost:8000 in your browser
Click “Start Chat” to begin your conversation!

You should see Cara appear in the video element and be ready to chat through voice interaction.

Now that you have a working basic app, let’s enhance it with production-ready features.

Listening to events

Anam personas communicate through an event system that allows your application to respond to connection changes, conversation updates, and user interactions. Let’s enhance our basic app with event handling to create a more responsive experience.

Understanding the Event System

The Anam SDK uses an event-driven architecture where you can listen for specific events and react accordingly. Here’s the process for listening to events:

Import the event types

Import the specific event types you want to listen to:

import { AnamEvent } from "https://esm.sh/@anam-ai/js-sdk@latest/dist/module/types";

Define your event listener function

Create a function to handle the event:

function onSessionReady() {
  console.log('Session Ready!');
  // Do something when the session is ready
}

Add your event listener to the client

anamClient.addListener(AnamEvent.SESSION_READY, onSessionReady);

For a full list of events, see the Event Handling documentation.

Now let’s implement this pattern in our app by adding a loading state.

Adding a loading state

Loading states provide important user feedback during connection establishment. Let’s add a simple loading indicator to our HTML:

Step 1: Update the UI

public/index.html

<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>Anam AI Assistant - Production App</title>
  </head>
  <body>
    <div style="text-align: center; padding: 20px;">
      <h1>Chat with Cara</h1>

      <div id="loading-message" style="display: none;">Loading...</div>

      <video
        id="persona-video"
        autoplay
        playsinline
        style="max-width: 100%; border-radius: 8px;"
      ></video>

      <div style="margin-top: 20px;">
        <button id="start-button">Start Chat</button>
        <button id="stop-button" disabled>Stop Chat</button>
      </div>
    </div>

    <script type="module" src="script.js"></script>
  </body>
</html>

Step 2: Adding the event listener

Now let’s update our JavaScript to handle the loading state by adding the following to our script.js file:

public/script.js

import { createClient } from "https://esm.sh/@anam-ai/js-sdk@latest";
import { AnamEvent } from "https://esm.sh/@anam-ai/js-sdk@latest/dist/module/types";

let anamClient = null;

// Get DOM elements
const startButton = document.getElementById("start-button");
const stopButton = document.getElementById("stop-button");
const videoElement = document.getElementById("persona-video");
const loadingMessage = document.getElementById("loading-message");

function showLoadingState() {
  if (loadingMessage) {
    loadingMessage.style.display = "block";
  }
}

function hideLoadingState() {
  if (loadingMessage) {
    loadingMessage.style.display = "none";
  }
}

async function startChat() {
  try {
    startButton.disabled = true;
    showLoadingState();

    // Get session token from your server
    const response = await fetch("/api/session-token", {
      method: "POST",
    });
    const { sessionToken } = await response.json();

    // Create the Anam client
    anamClient = createClient(sessionToken);

    // Listen for SESSION_READY event to hide loading state
    anamClient.addListener(AnamEvent.SESSION_READY, () => {
      console.log("Session is ready!");
      hideLoadingState();
      startButton.disabled = true;
      stopButton.disabled = false;
    });

    // Start streaming to the video element
    await anamClient.streamToVideoElement("persona-video");

    console.log("Chat started successfully!");
  } catch (error) {
    console.error("Failed to start chat:", error);
    startButton.disabled = false;
    hideLoadingState();
  }
}

function stopChat() {
  if (anamClient) {
    // Disconnect the client
    anamClient.stopStreaming();
    anamClient = null;

    // Clear video element
    videoElement.srcObject = null;

    // Update button states
    startButton.disabled = false;
    stopButton.disabled = true;

    console.log("Chat stopped.");
  }
}

// Add event listeners
startButton.addEventListener("click", startChat);
stopButton.addEventListener("click", stopChat);

Adding a chat history panel

A common use case for event listeners is to update the UI based on the transcription of the conversation. Let’s look at how we can implement this using Anam events.

Understanding Message Events

Anam provides two key events for tracking conversation transcriptions:

Event	Description
`MESSAGE_HISTORY_UPDATED`	Provides the complete conversation history each time someone finishes speaking
`MESSAGE_STREAM_EVENT_RECEIVED`	Provides real-time transcription updates as speech occurs

Let’s start with the MESSAGE_HISTORY_UPDATED event to build a basic chat history.

Step 1: Add chat history UI

First, update your HTML to include a simple chat panel:

public/index.html

<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>Anam AI Assistant - Production App</title>
  </head>
  <body>
    <div style="text-align: center; padding: 20px;">
      <h1>Chat with Cara</h1>

      <div id="loading-message" style="display: none;">Loading...</div>

      <video
        id="persona-video"
        autoplay
        playsinline
        style="max-width: 100%; border-radius: 8px;"
      ></video>

      <!-- Chat History Panel -->
      <div
        id="chat-history"
        style="margin-top: 20px; padding: 10px; border: 1px solid #ccc; border-radius: 5px; max-height: 200px; overflow-y: auto;"
      >
        <p>Start a conversation to see your chat history</p>
      </div>

      <div style="margin-top: 20px;">
        <button id="start-button">Start Chat</button>
        <button id="stop-button" disabled>Stop Chat</button>
      </div>
    </div>

    <script type="module" src="script.js"></script>
  </body>
</html>

Step 2: Listen for updates

Now let’s add the event listener to handle complete conversation updates:

public/script.js

import { createClient } from "https://esm.sh/@anam-ai/js-sdk@latest";
import { AnamEvent } from "https://esm.sh/@anam-ai/js-sdk@latest/dist/module/types";

let anamClient = null;

// Get DOM elements
const startButton = document.getElementById("start-button");
const stopButton = document.getElementById("stop-button");
const videoElement = document.getElementById("persona-video");
const loadingMessage = document.getElementById("loading-message");
const chatHistory = document.getElementById("chat-history");

function showLoadingState() {
  if (loadingMessage) {
    loadingMessage.style.display = "block";
  }
}

function hideLoadingState() {
  if (loadingMessage) {
    loadingMessage.style.display = "none";
  }
}

function updateChatHistory(messages) {
  if (!chatHistory) return;
  // Clear existing content
  chatHistory.innerHTML = "";
  if (messages.length === 0) {
    chatHistory.innerHTML =
      "<p>Start a conversation to see your chat history</p>";
    return;
  }
  // Add each message to the chat history
  messages.forEach((message) => {
    const messageDiv = document.createElement("div");
    messageDiv.style.marginBottom = "10px";
    messageDiv.style.padding = "5px";
    messageDiv.style.borderRadius = "5px";
    if (message.role === "user") {
      messageDiv.style.backgroundColor = "#e3f2fd";
      messageDiv.innerHTML = `<strong>You:</strong> ${message.content}`;
    } else {
      messageDiv.style.backgroundColor = "#f1f8e9";
      messageDiv.innerHTML = `<strong>Cara:</strong> ${message.content}`;
    }
    chatHistory.appendChild(messageDiv);
  });
  // Scroll to bottom
  chatHistory.scrollTop = chatHistory.scrollHeight;
}

async function startChat() {
  try {
    startButton.disabled = true;
    showLoadingState();

    // Get session token from your server
    const response = await fetch("/api/session-token", {
      method: "POST",
    });
    const { sessionToken } = await response.json();

    // Create the Anam client
    anamClient = createClient(sessionToken);

    // Listen for SESSION_READY event to hide loading state
    anamClient.addListener(AnamEvent.SESSION_READY, () => {
      console.log("Session is ready!");
      hideLoadingState();
      startButton.disabled = true;
      stopButton.disabled = false;
    });

    // Listen for MESSAGE_HISTORY_UPDATED to update chat history
    anamClient.addListener(AnamEvent.MESSAGE_HISTORY_UPDATED, (messages) => {
      console.log("Conversation updated:", messages);
      updateChatHistory(messages);
    });

    // Start streaming to the video element
    await anamClient.streamToVideoElement("persona-video");

    console.log("Chat started successfully!");
  } catch (error) {
    console.error("Failed to start chat:", error);
    startButton.disabled = false;
    hideLoadingState();
  }
}

function stopChat() {
  if (anamClient) {
    // Disconnect the client
    anamClient.stopStreaming();
    anamClient = null;

    // Clear video element and chat history
    videoElement.srcObject = null;
    updateChatHistory([]);

    // Update button states
    startButton.disabled = false;
    stopButton.disabled = true;

    console.log("Chat stopped.");
  }
}

// Add event listeners
startButton.addEventListener("click", startChat);
stopButton.addEventListener("click", stopChat);

The MESSAGE_HISTORY_UPDATED event provides an array of message objects with role (“user” or “assistant”) and content properties. This gives you the complete conversation transcript each time someone finishes speaking.

Step 3: Add real-time transcription

Now let’s enhance the experience by showing live transcription as the persona speaks using the MESSAGE_STREAM_EVENT_RECEIVED event:

<!-- Add this to your HTML after the chat history -->
<div
  id="live-transcript"
  style="margin-top: 10px; padding: 10px; background-color: #e6e0ff; border-radius: 5px;"
>
  <strong>Persona Live:</strong> <span id="transcript-text"></span>
</div>

And update your JavaScript to handle real-time events:

// Add this event listener inside your startChat function after the MESSAGE_HISTORY_UPDATED listener

// Listen for real-time transcription events
anamClient.addListener(AnamEvent.MESSAGE_STREAM_EVENT_RECEIVED, (event) => {
  const liveTranscript = document.getElementById("live-transcript");
  const transcriptText = document.getElementById("transcript-text");

  console.log("event", event);

  if (event.role === "persona") {
    // Show persona speaking in real-time
    if (liveTranscript && transcriptText) {
      transcriptText.textContent = transcriptText.textContent + event.content;
    }
  } else if (event.role === "user") {
    // clear the persona live transcript when the user speaks
    if (liveTranscript && transcriptText) {
      transcriptText.textContent = "";
    }
  }
});

The MESSAGE_STREAM_EVENT_RECEIVED event fires continuously as speech is being processed. Use event.role to distinguish between “persona” (AI speaking) and “user” (user speaking) events.

Your app now displays both complete conversation history and real-time transcription as the persona speaks!

Sending commands

Beyond voice interaction, you can programmatically send messages to your persona using the talk command. This is useful for creating interactive experiences, automated workflows, or custom UI controls.

Using the talk command

The talk command allows you to send text messages that the persona will speak directly. This can be used to instruct the persona to say something in response to a user action other than voice input, such as a button click or when certain UI elements are shown on screen. You can send a talk command by calling the talk method on the Anam client during a session.

anamClient.talk("Hello, how are you?");

Let’s use this to add a talk command UI to our app.

Step 1: Update the UI

First, update your HTML to include a text input and send button

public/index.html

<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>Anam AI Assistant - Production App</title>
  </head>
  <body>
    <div style="text-align: center; padding: 20px;">
      <h1>Chat with Cara</h1>

      <div id="loading-message" style="display: none;">Loading...</div>

      <video
        id="persona-video"
        autoplay
        playsinline
        style="max-width: 100%; border-radius: 8px;"
      ></video>

      <!-- Chat History Panel -->
      <div
        id="chat-history"
        style="margin-top: 20px; padding: 10px; border: 1px solid #ccc; border-radius: 5px; max-height: 200px; overflow-y: auto;"
      >
        <p>Start a conversation to see your chat history</p>
      </div>

      <!-- Live Transcript -->
      <div
        id="live-transcript"
        style="margin-top: 10px; padding: 10px; background-color: #e6e0ff; border-radius: 5px;"
      >
        <strong>Persona Live:</strong> <span id="transcript-text"></span>
      </div>

      <!-- Talk Command Panel -->
      <div
        style="margin-top: 20px; padding: 15px; border: 1px solid #ccc; border-radius: 5px;"
      >
        <h3 style="margin: 0 0 10px 0;">Send Message</h3>
        <div style="display: flex; gap: 10px; align-items: flex-end;">
          <textarea
            id="message-input"
            placeholder="Type a message for Cara to respond to..."
            rows="3"
            style="flex: 1; padding: 10px; border: 1px solid #ddd; border-radius: 4px; font-family: inherit;"
          ></textarea>
          <button
            id="send-message"
            disabled
            style="padding: 10px 20px; border: none; border-radius: 4px; background: #4CAF50; color: white; cursor: pointer;"
          >
            Send Message
          </button>
        </div>
      </div>

      <div style="margin-top: 20px;">
        <button id="start-button">Start Chat</button>
        <button id="stop-button" disabled>Stop Chat</button>
      </div>
    </div>

    <script type="module" src="script.js"></script>
  </body>
</html>

Step 2: Add the code

Now let’s add the code to our script.js file to send the command to the persona

public/script.js

// Add these functions to your existing script.js file

async function sendTalkMessage() {
  const messageInput = document.getElementById("message-input");
  const sendButton = document.getElementById("send-message");

  if (!anamClient || !messageInput) return;

  const message = messageInput.value.trim();
  if (!message) {
    alert("Please enter a message");
    return;
  }

  try {
    sendButton.disabled = true;
    sendButton.textContent = "Sending...";

    // Send the message to the persona
    await anamClient.talk(message);

    // Clear the input
    messageInput.value = "";
  } catch (error) {
    console.error("Failed to send message:", error);
    alert("Failed to send message. Please try again.");
  } finally {
    sendButton.disabled = false;
    sendButton.textContent = "Send Message";
  }
}

function updateTalkControls(connected) {
  const sendButton = document.getElementById("send-message");
  const messageInput = document.getElementById("message-input");

  if (sendButton) {
    sendButton.disabled = !connected;
    sendButton.style.opacity = connected ? "1" : "0.5";
  }

  if (messageInput) {
    messageInput.disabled = !connected;
    messageInput.placeholder = connected
      ? "Type a message for Cara to respond to..."
      : "Connect to start chatting...";
  }
}

// Update your startChat function to enable talk controls
async function startChat() {
  try {
    startButton.disabled = true;
    showLoadingState();

    const response = await fetch("/api/session-token", {
      method: "POST",
    });
    const { sessionToken } = await response.json();

    anamClient = createClient(sessionToken);

    anamClient.addListener(AnamEvent.SESSION_READY, () => {
      console.log("Session is ready!");
      hideLoadingState();
      startButton.disabled = true;
      stopButton.disabled = false;
      updateTalkControls(true); // Enable talk controls
    });

    anamClient.addListener(AnamEvent.MESSAGE_HISTORY_UPDATED, (messages) => {
      console.log("Conversation updated:", messages);
      updateChatHistory(messages);
    });

    anamClient.addListener(AnamEvent.MESSAGE_STREAM_EVENT_RECEIVED, (event) => {
      const liveTranscript = document.getElementById("live-transcript");
      const transcriptText = document.getElementById("transcript-text");

      if (event.role === "persona") {
        if (liveTranscript && transcriptText) {
          transcriptText.textContent =
            transcriptText.textContent + event.content;
        }
      } else if (event.role === "user") {
        if (liveTranscript && transcriptText) {
          transcriptText.textContent = "";
        }
      }
    });

    await anamClient.streamToVideoElement("persona-video");

    console.log("Chat started successfully!");
  } catch (error) {
    console.error("Failed to start chat:", error);
    startButton.disabled = false;
    hideLoadingState();
  }
}

// Add event listeners for talk functionality
document.addEventListener("DOMContentLoaded", () => {
  const sendButton = document.getElementById("send-message");
  const messageInput = document.getElementById("message-input");

  if (sendButton) {
    sendButton.addEventListener("click", sendTalkMessage);
  }

  if (messageInput) {
    // Send message with Enter key (Shift+Enter for new line)
    messageInput.addEventListener("keydown", (e) => {
      if (e.key === "Enter" && !e.shiftKey) {
        e.preventDefault();
        sendTalkMessage();
      }
    });
  }
});

Advanced Stream Management

For applications that require more control over audio and video streams, you have two main approaches for customizing the streaming behavior:

Custom Input Streams: Pass your own audio input to streamToVideoElement
Output Stream Capture: Use stream() to capture and process persona output

Custom Input Streams

The streamToVideoElement() method accepts an optional audio input stream, allowing you to process or record user audio before sending it to the persona:

// Get and potentially process user audio
const userInputStream = await navigator.mediaDevices.getUserMedia({
  audio: true,
});

// Start recording user input
const userRecorder = new MediaRecorder(userInputStream);
userRecorder.start();

// Use the same stream for persona input
await anamClient.streamToVideoElement("persona-video", userInputStream);

This approach is useful when you want to:

Record user audio input
Apply audio filters or effects to user input
Monitor user audio levels
Handle custom microphone setups

Output Stream Capture

For capturing and processing the persona’s output (video and audio), use the stream() method which returns the raw output streams:

const userInputStream = await navigator.mediaDevices.getUserMedia({
  audio: true,
});
const [videoStream] = await anamClient.stream(userInputStream);

// Now you have full control over the output stream
videoElement.srcObject = videoStream;

// Extract audio for separate processing
const audioTracks = videoStream.getAudioTracks();
const personaAudioStream = new MediaStream(audioTracks);

This approach enables:

Recording persona video and audio output
Custom video rendering and effects
Audio analysis and processing
Streaming to multiple destinations

What You’ve Built

You now have a working Anam application with these core patterns:

WebRTC Streaming: Real-time video connection for voice conversations with an AI persona
Event Handling: Responding to session state changes and conversation updates using the SDK’s event system
Live Transcription: Real-time display of what the persona is saying via MESSAGE_STREAM_EVENT_RECEIVED
Conversation History: Complete transcript tracking via MESSAGE_HISTORY_UPDATED
Talk Commands: Programmatic text input to trigger persona responses
Session Management: Secure server-side token generation with proper API key protection
Stream Recording: Manual stream management for custom audio processing workflows

What’s Next

Ready to take your persona application further? Here are your next steps: Explore Advanced Features: Continue reading our guides to learn about audio control, custom personas, and production deployment best practices. Integrate Your Own AI: Want to use your own language model instead of Anam’s default brain? Check out our Custom LLM Integration guide to learn how to connect your persona to custom AI models and APIs.

Advanced Customization

Persona Configuration

Modify the getDefaultPersonaConfig() method to customize:

Avatar appearance and voice selection
System prompts and personality traits
Custom brain types and LLM integration

UI Theming

Update the CSS variables in app.css to match your brand:

Color schemes and gradients
Typography and spacing
Animation timing and effects

Event Integration

Extend the event handlers to integrate with your existing systems:

Analytics and user behavior tracking
Customer service platforms
CRM and database systems

Troubleshooting

Connection Issues

Symptoms: Persona fails to connect or frequently disconnectsSolutions:

Verify your API key is correctly configured
Check network connectivity and firewall settings
Ensure WebRTC is supported in your browser
Review server logs for authentication errors

Audio Problems

Symptoms: No audio input/output or poor qualitySolutions:

Grant microphone permissions in browser settings
Check audio device configuration
Ensure HTTPS is enabled (required for microphone access)
Test with different browsers or devices

Performance Issues

Symptoms: Slow loading or laggy interactionsSolutions:

Optimize network bandwidth and connection quality
Reduce video quality if needed
Implement connection pooling and caching
Monitor server resource usage

UI Responsiveness

Symptoms: Interface doesn’t work on mobile or different screen sizesSolutions:

Test on various devices and screen sizes
Verify CSS media queries are working
Check touch event handling
Validate accessibility compliance

Getting Started

SDK Reference

Examples

Full application

How to use this guide

What You’ll Build

Prerequisites

Basic App

Step 1: Set up your server

Step 2: Set up your HTML

Step 3: Initialize the Anam client

Step 4: Test your basic setup

Listening to events

Understanding the Event System

Adding a loading state

Step 1: Update the UI

Step 2: Adding the event listener

Adding a chat history panel

Understanding Message Events

Step 1: Add chat history UI

Step 2: Listen for updates

Step 3: Add real-time transcription

Sending commands

Using the talk command

Step 1: Update the UI

Step 2: Add the code

Advanced Stream Management

Custom Input Streams

Output Stream Capture

What You’ve Built

What’s Next

Advanced Customization

Persona Configuration

UI Theming

Event Integration

Troubleshooting

​How to use this guide

​What You’ll Build

​Prerequisites

​Basic App

​Step 1: Set up your server

​Step 2: Set up your HTML

​Step 3: Initialize the Anam client

​Step 4: Test your basic setup

​Listening to events

​Understanding the Event System

​Adding a loading state

​Step 1: Update the UI

​Step 2: Adding the event listener

​Adding a chat history panel

​Understanding Message Events

​Step 1: Add chat history UI

​Step 2: Listen for updates

​Step 3: Add real-time transcription

​Sending commands

​Using the talk command

​Step 1: Update the UI

​Step 2: Add the code

​Advanced Stream Management

​Custom Input Streams

​Output Stream Capture

​What You’ve Built

​What’s Next

​Advanced Customization

​Persona Configuration

​UI Theming

​Event Integration

​Troubleshooting

How to use this guide

What You’ll Build

Prerequisites

Basic App

Step 1: Set up your server

Step 2: Set up your HTML

Step 3: Initialize the Anam client

Step 4: Test your basic setup

Listening to events

Understanding the Event System

Adding a loading state

Step 1: Update the UI

Step 2: Adding the event listener

Adding a chat history panel

Understanding Message Events

Step 1: Add chat history UI

Step 2: Listen for updates

Step 3: Add real-time transcription

Sending commands

Using the talk command

Step 1: Update the UI

Step 2: Add the code

Advanced Stream Management

Custom Input Streams

Output Stream Capture

What You’ve Built

What’s Next

Advanced Customization

Persona Configuration

UI Theming

Event Integration

Troubleshooting