Zoom Video SDK Web
OpenAIOfficialCreated by ZoomDistributed by OpenAI
- Skill
- Tool integration
- Software development
- MIT
- No issues found
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The Zoom Video SDK for Web provides a robust JavaScript/TypeScript library for building custom, browser-based video communication experiences. Unlike standard Zoom meetings, this SDK allows developers to create fully branded, custom user interfaces for video sessions, screen sharing, live transcription, and collaborative features like whiteboarding. It follows a strict event-driven architecture and requires careful management of the session lifecycle, particularly regarding media stream initialization and participant event handling.
What it does
- Enables real-time audio and video communication in web browsers.
- Supports screen sharing and collaborative whiteboarding.
- Provides tools for cloud recording and live streaming to RTMP endpoints.
- Includes features for in-session chat and custom command messaging.
- Facilitates live transcription and breakout room management.
- Offers granular control over media devices and video quality settings.
When to use it
- When building a custom-branded video conferencing application.
- When you need full control over the video UI and participant layout.
- When integrating real-time communication into existing web platforms.
- When requiring advanced features like custom video frame processing or live captions.
Advantages
- Full control over the user interface and user experience.
- Supports high-definition video and WebRTC for direct peer-to-peer streaming.
- Comprehensive feature set including chat, recording, and transcription.
- Well-documented lifecycle patterns for reliable session management.
Usage examples
- “How do I join a video session using the Zoom Video SDK?”
- The user receives the 5-step lifecycle pattern: create client, initialize, join, get media stream, and start media, with specific warnings to only call getMediaStream() after joining.
- “How can I display a remote participant's video?”
- The user is guided to use the peer-video-state-change event to trigger attachVideo() and append the resulting video element to the DOM.
Install
Download the skill as a ZIP:
https://autogineer.com/agent-skills/openai/zoom-video-sdk-web/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip zoom-video-sdk-web.zip -d .agents/skills
Documentation by Zoom
Zoom Video SDK - Web Development
Expert guidance for developing with the Zoom Video SDK on Web. This SDK enables custom video applications in the browser with real-time video/audio, screen sharing, cloud recording, live streaming, chat, and live transcription.
This skill is for custom video sessions, not embedded Zoom meetings. If the user wants a custom UI for a real Zoom meeting, route to ../../meeting-sdk/web/component-view/SKILL.md.
Official Documentation: https://developers.zoom.us/docs/video-sdk/web/ API Reference: https://marketplacefront.zoom.us/sdk/custom/web/modules.html Sample Repository: https://github.com/zoom/videosdk-web-sample
Quick Links
New to Video SDK? Follow this path:
SDK Architecture Pattern - Universal 3-step pattern for ANY feature
Session Join Pattern - Complete working code to join a session
Video Rendering - Display video with attachVideo()
Event Handling - Required events for video/audio
Reference:
Singleton Hierarchy - 4-level SDK navigation map
API Reference - Methods, events, error codes
SKILL.md - Complete documentation navigation
../../probe-sdk/SKILL.md - Optional browser/device/network readiness diagnostics before join
Having issues?
Video not showing → Video Rendering (use attachVideo, not renderVideo)
getMediaStream() returns undefined → Call AFTER join() completes
Quick diagnostics → Common Issues
SDK Overview
The Zoom Video SDK for Web is a JavaScript library that provides:
Session Management: Join/leave video SDK sessions
Video/Audio: Start/stop camera and microphone
Screen Sharing: Share screens or browser tabs
Cloud Recording: Record sessions to Zoom cloud
Live Streaming: Stream to RTMP endpoints
Chat: In-session messaging
Command Channel: Custom command messaging
Live Transcription: Real-time speech-to-text
Subsessions: Breakout room support
Whiteboard: Collaborative whiteboard features
Virtual Background: Blur or custom image backgrounds
Prerequisites
System Requirements
Modern Browser: Chrome 80+, Firefox 75+, Safari 14+, Edge 80+
Video SDK Credentials: SDK Key and Secret from Marketplace
JWT Token: Server-side generated signature
Browser Feature Requirements
// Check browser compatibility before init
const compatibility = ZoomVideo.checkSystemRequirements();
console.log('Audio:', compatibility.audio);
console.log('Video:', compatibility.video);
console.log('Screen:', compatibility.screen);
// Check feature support
const features = ZoomVideo.checkFeatureRequirements();
console.log('Supported:', features.supportFeatures);
console.log('Unsupported:', features.unSupportFeatures);Optional Pre-Join Diagnostics (Recommended for Reliability)
Use Probe SDK as a readiness gate before client.join(...) when you need to reduce failed starts:
Run diagnostics with ../../probe-sdk/SKILL.md.
Evaluate policy (
allow,warn,block).Start Video SDK join only when policy allows.
Cross-skill flow: ../../general/use-cases/probe-sdk-preflight-readiness-gate.md
Installation
NPM (Recommended)
npm install @zoom/videosdkimport ZoomVideo from '@zoom/videosdk';CDN (Fallback Strategy Recommended)
Note: Some networks/ad blockers can block
source.zoom.us. If you see flaky loads, first try allowlisting the domain in your environment. If needed, consider a fallback (mirror/self-host) only if it's permitted for your use case and you can keep versions in sync.
# Download SDK locally
curl "https://source.zoom.us/videosdk/zoom-video-2.3.12.min.js" -o public/js/zoom-video-sdk.min.js<!-- Use local copy instead of CDN -->
<script src="js/zoom-video-sdk.min.js"></script>// CDN exports as WebVideoSDK, NOT ZoomVideo
const ZoomVideo = WebVideoSDK.default;Quick Start
import ZoomVideo from '@zoom/videosdk';
// 1. Create client (singleton - returns same instance)
const client = ZoomVideo.createClient();
// 2. Initialize SDK
await client.init('en-US', 'Global', { patchJsMedia: true });
// 3. Join session
await client.join(topic, signature, userName, password);
// 4. CRITICAL: Get stream AFTER join
const stream = client.getMediaStream();
// 5. Start media
await stream.startVideo();
await stream.startAudio();
// 6. Attach video to DOM
const videoElement = await stream.attachVideo(userId, VideoQuality.Video_360P);
document.getElementById('video-container').appendChild(videoElement);SDK Lifecycle (CRITICAL ORDER)
The SDK has a strict lifecycle. Violating it causes silent failures.
1. Create client: client = ZoomVideo.createClient()
2. Initialize: await client.init('en-US', 'Global', options)
3. Join session: await client.join(topic, signature, userName, password)
4. Get stream: stream = client.getMediaStream() ← ONLY AFTER JOIN
5. Start media: await stream.startVideo() / await stream.startAudio()Common Mistake:
// WRONG: Getting stream before joining
const stream = client.getMediaStream(); // Returns undefined!
await client.join(...);
// CORRECT: Get stream after joining
await client.join(...);
const stream = client.getMediaStream(); // Works!Critical Gotchas and Best Practices
getMediaStream() ONLY Works After join()
The #1 issue that causes video/audio to fail:
// WRONG
const stream = client.getMediaStream(); // undefined!
await client.join(...);
// CORRECT
await client.join(...);
const stream = client.getMediaStream(); // WorksUse attachVideo() NOT renderVideo()
renderVideo() is deprecated. Use attachVideo() which returns a VideoPlayer element:
import { VideoQuality } from '@zoom/videosdk';
// CORRECT: attachVideo returns element to append
const videoElement = await stream.attachVideo(userId, VideoQuality.Video_360P);
document.getElementById('video-container').appendChild(videoElement);
// WRONG: renderVideo is deprecated
await stream.renderVideo(canvas, userId, ...); // Don't use!Video Rendering is Event-Driven (CRITICAL)
You MUST listen for events to properly render participant videos:
// When another participant's video state changes
client.on('peer-video-state-change', async (payload) => {
const { action, userId } = payload;
if (action === 'Start') {
// Participant turned on video - attach it
const element = await stream.attachVideo(userId, VideoQuality.Video_360P);
container.appendChild(element);
} else if (action === 'Stop') {
// Participant turned off video - detach it
await stream.detachVideo(userId);
}
});
// When participants join/leave
client.on('user-added', (payload) => {
// New participant joined - check if their video is on
const users = client.getAllUser();
// Render videos for users with bVideoOn === true
});
client.on('user-removed', (payload) => {
// Participant left - clean up their video element
stream.detachVideo(payload[0].userId);
});Peer Video on Mid-Session Join
Existing participants' videos won't auto-render when you join mid-session.
// After joining, render existing participants' videos
const renderExistingVideos = async () => {
await new Promise(resolve => setTimeout(resolve, 500));
const users = client.getAllUser();
const currentUserId = client.getCurrentUserInfo().userId;
for (const user of users) {
if (user.bVideoOn && user.userId !== currentUserId) {
const element = await stream.attachVideo(user.userId, VideoQuality.Video_360P);
document.getElementById(`video-${user.userId}`).appendChild(element);
}
}
};CDN Race Condition with ES Modules
When using <script type="module"> with CDN, the SDK may not be loaded yet:
function waitForSDK(timeout = 10000) {
return new Promise((resolve, reject) => {
if (typeof WebVideoSDK !== 'undefined') {
resolve();
return;
}
const start = Date.now();
const check = setInterval(() => {
if (typeof WebVideoSDK !== 'undefined') {
clearInterval(check);
resolve();
} else if (Date.now() - start > timeout) {
clearInterval(check);
reject(new Error('SDK failed to load'));
}
}, 100);
});
}
await waitForSDK();
const ZoomVideo = WebVideoSDK.default;SharedArrayBuffer for HD Video
For optimal performance and HD video, configure these headers on your server:
Cross-Origin-Opener-Policy: same-origin
Cross-Origin-Embedder-Policy: require-corpNote: As of v1.11.2, SharedArrayBuffer is elective (not strictly required).
Check HD Capability Before Enabling
const stream = client.getMediaStream();
// Check if 720p is supported
const hdSupported = stream.isSupportHDVideo();
// Get maximum video quality
const maxQuality = stream.getVideoMaxQuality();
// 0=90P, 1=180P, 2=360P, 3=720P, 4=1080P
// Start video with HD
if (hdSupported) {
await stream.startVideo({ hd: true });
}Screen Share Rendering Mode Check
const stream = client.getMediaStream();
// Check which element type to use
if (stream.isStartShareScreenWithVideoElement()) {
// Use video element
const video = document.getElementById('share-video');
await stream.startShareScreen(video as unknown as HTMLCanvasElement);
} else {
// Use canvas element
const canvas = document.getElementById('share-canvas');
await stream.startShareScreen(canvas);
}Key Features
Video Quality Enum
import { VideoQuality } from '@zoom/videosdk';
VideoQuality.Video_90P // 0
VideoQuality.Video_180P // 1
VideoQuality.Video_360P // 2 (recommended for most cases)
VideoQuality.Video_720P // 3
VideoQuality.Video_1080P // 4Virtual Backgrounds
const stream = client.getMediaStream();
// Always check support first
if (stream.isSupportVirtualBackground()) {
// Blur background
await stream.updateVirtualBackgroundImage('blur');
// Custom image background
await stream.updateVirtualBackgroundImage('https://example.com/bg.jpg');
// Remove virtual background
await stream.updateVirtualBackgroundImage(undefined);
}Video Processor (Custom Effects)
The VideoProcessor class allows you to intercept and modify video frames:
// video-processor-worker.js
class MyVideoProcessor extends VideoProcessor {
processFrame(input, output) {
const ctx = output.getContext('2d');
ctx.drawImage(input, 0, 0);
// Add overlay
ctx.fillStyle = 'white';
ctx.font = '24px Arial';
ctx.fillText('Live', 20, 40);
return true;
}
}WebRTC Mode
Enable WebRTC mode for direct peer-to-peer streaming with HD video support:
await client.init('en-US', 'Global', {
patchJsMedia: true,
webrtc: true // Enable WebRTC mode
});Feature Clients
Access specialized clients from the VideoClient:
| Client | Access Method | Purpose |
|---|---|---|
| Stream | client.getMediaStream() | Video, audio, screen share, devices |
| Chat | client.getChatClient() | Send/receive messages |
| Command | client.getCommandClient() | Custom commands (reactions, etc.) |
| Recording | client.getRecordingClient() | Cloud recording control |
| Transcription | client.getLiveTranscriptionClient() | Live captions |
| LiveStream | client.getLiveStreamClient() | RTMP streaming |
| Subsession | client.getSubsessionClient() | Breakout rooms |
| Whiteboard | client.getWhiteboardClient() | Collaborative whiteboard |
Common Tasks
Start/Stop Video
await stream.startVideo();
await stream.stopVideo();Start/Stop Audio
await stream.startAudio();
await stream.muteAudio();
await stream.unmuteAudio();
await stream.stopAudio();Switch Devices
// Get available devices
const cameras = stream.getCameraList();
const mics = stream.getMicList();
const speakers = stream.getSpeakerList();
// Switch devices
await stream.switchCamera(cameraId);
await stream.switchMicrophone(micId);
await stream.switchSpeaker(speakerId);Screen Sharing
// Start sharing
await stream.startShareScreen(canvas);
// Stop sharing
await stream.stopShareScreen();
// Receive share
client.on('active-share-change', async (payload) => {
if (payload.state === 'Active') {
await stream.startShareView(canvas, payload.userId);
} else {
await stream.stopShareView();
}
});Chat
const chatClient = client.getChatClient();
// Send to everyone
await chatClient.send('Hello, everyone!');
// Send to specific user
await chatClient.sendToUser(userId, 'Private message');
// Receive messages
client.on('chat-on-message', (payload) => {
console.log(`${payload.sender.name}: ${payload.message}`);
});Recording (Host Only)
const recordingClient = client.getRecordingClient();
await recordingClient.startCloudRecording();
await recordingClient.stopCloudRecording();
client.on('recording-change', (payload) => {
console.log('Recording status:', payload.state);
});Leave/End Session
// Leave session (others stay)
await client.leave();
// End session for ALL participants (host only)
await client.leave(true);Error Handling
Common Join Errors
| Error | Cause | Solution |
|---|---|---|
Invalid signature | JWT expired or malformed | Generate new signature |
Session does not exist | Host hasn't started yet | Show "waiting" message, retry |
Permission denied | User denied camera/mic | Request permission again |
Example Error Handler
try {
await client.join(topic, signature, userName, password);
} catch (error) {
if (error.reason?.includes('signature')) {
// Regenerate signature and retry
} else if (error.reason?.includes('Session')) {
// Show "Waiting for host..." and poll
} else if (error.reason?.includes('Permission')) {
// Guide user to enable permissions
}
console.error('Join failed:', error);
}Browser Compatibility
| Feature | Chrome | Firefox | Safari | Edge |
|---|---|---|---|---|
| Video | 80+ | 75+ | 14+ | 80+ |
| Audio | 80+ | 75+ | 14+ | 80+ |
| Screen Share | 80+ | 75+ | 15+ | 80+ |
| Virtual BG | 80+ | 90+ | - | 80+ |
Safari Notes:
Virtual background not supported
Screen sharing requires macOS 15+
CORS Errors (Telemetry)
CORS errors to log-external-gateway.zoom.us are harmless.
These are caused by COOP/COEP headers blocking telemetry requests. They don't affect SDK functionality.
Complete Documentation Library
Core Concepts
SDK Architecture Pattern - Universal 3-step pattern for ANY feature
Singleton Hierarchy - 4-level navigation guide
Complete Examples
Session Join Pattern - JWT auth + session join with full code
Video Rendering - attachVideo() patterns
Screen Share - Send and receive screen shares
Event Handling - Required events
Chat - In-session messaging
Recording - Cloud recording control
Transcription - Live captions
Framework Integrations
React Hooks - Official @zoom/videosdk-react library
Framework Integrations - Next.js, Vue/Nuxt patterns
Troubleshooting
Common Issues - Quick diagnostics & error codes
References
API Reference - Complete method signatures
Events Reference - All event types
SKILL.md - Complete navigation guide
Official Sample Repositories
| Type | Repository |
|---|---|
| Web Sample | videosdk-web-sample |
| React SDK | videosdk-react |
| Next.js | videosdk-nextjs-quickstart |
| Vue/Nuxt | videosdk-vue-nuxt-quickstart |
| Auth Endpoint | videosdk-auth-endpoint-sample |
| UI Toolkit | videosdk-zoom-ui-toolkit-react-sample |
Resources
Official Docs: https://developers.zoom.us/docs/video-sdk/web/
API Reference: https://marketplacefront.zoom.us/sdk/custom/web/modules.html
Dev Forum: https://devforum.zoom.us/
GitHub Samples: https://github.com/zoom/videosdk-web-sample
Need help? Start with SKILL.md for complete navigation.
Merged from video-sdk/web/SKILL.md
Zoom Video SDK Web - Complete Documentation Index
Quick Start Path
If you're new to the SDK, follow this order:
Read the architecture pattern → concepts/sdk-architecture-pattern.md
Universal formula: Create Client → Init → Join → Get Stream → Use
Once you understand this, you can implement any feature
Implement session join → examples/session-join-pattern.md
Complete working JWT + session join code
Listen to events → examples/event-handling.md
CRITICAL: The SDK is event-driven, you must listen for events
Implement video → examples/video-rendering.md
Use attachVideo(), NOT renderVideo()
Troubleshoot any issues → troubleshooting/common-issues.md
Quick diagnostic checklist
Error code tables
Documentation Structure
video-sdk/web/
├── SKILL.md # Main skill overview
├── SKILL.md # This file - navigation guide
│
├── concepts/ # Core architectural patterns
│ ├── sdk-architecture-pattern.md # Universal formula for ANY feature
│ └── singleton-hierarchy.md # 4-level navigation guide
│
├── examples/ # Complete working code
│ ├── session-join-pattern.md # JWT auth + session join
│ ├── video-rendering.md # attachVideo() patterns
│ ├── screen-share.md # Send and receive screen shares
│ ├── event-handling.md # Required events
│ ├── chat.md # Chat implementation
│ ├── command-channel.md # Command channel messaging
│ ├── recording.md # Cloud recording control
│ ├── transcription.md # Live transcription/captions
│ ├── react-hooks.md # Official @zoom/videosdk-react library
│ └── framework-integrations.md # Next.js, Vue/Nuxt, ZFG patterns
│
├── troubleshooting/ # Problem solving guides
│ └── common-issues.md # Quick diagnostic workflow
│
└── references/ # Reference documentation
├── web-reference.md # API hierarchy, methods, error codes
└── events-reference.md # All event typesBy Use Case
I want to build a video app
SDK Architecture Pattern - Understand the pattern
Session Join Pattern - Join sessions
Video Rendering - Display video
Event Handling - Listen for video events
I'm getting runtime errors
Common Issues - Error code tables
"getMediaStream() is undefined" → Call AFTER join() completes
I want to receive screen shares
Screen Share - startShareView() patterns
Event Handling - active-share-change event
I want to send screen shares
Screen Share - startShareScreen() patterns
Check isStartShareScreenWithVideoElement() for element type
I want to use chat
Chat - Send/receive messages
getChatClient() for ChatClient access
I want to record sessions
Recording - Cloud recording (host only)
getRecordingClient() for RecordingClient access
I want to use live transcription
Transcription - Enable live captions
getLiveTranscriptionClient() for LiveTranscriptionClient access
I want to use command channel
Command Channel - Custom signaling between participants
Must call getCommandClient() AFTER join()
I want to implement a specific feature
SDK Architecture Pattern - START HERE!
Singleton Hierarchy - Navigate to the feature
API Reference - Method signatures
I'm using React
React Hooks - Official @zoom/videosdk-react library
Provides hooks: useSession, useSessionUsers, useVideoState, useAudioState
Pre-built components: VideoPlayerComponent, ScreenSharePlayerComponent
I'm using Next.js or Vue/Nuxt
Framework Integrations - SSR considerations
Server-side JWT generation patterns
Client-side only SDK usage
Most Critical Documents
1. SDK Architecture Pattern (MASTER DOCUMENT)
concepts/sdk-architecture-pattern.md
The universal 5-step pattern:
Create client
Initialize SDK
Join session
Get stream
Use features + listen to events
2. Common Issues (MOST COMMON PROBLEMS)
troubleshooting/common-issues.md
Common issues:
getMediaStream() returns undefined
Video not displaying
renderVideo() deprecated
3. Singleton Hierarchy (NAVIGATION MAP)
concepts/singleton-hierarchy.md
4-level deep navigation showing how to reach every feature.
Key Learnings
Critical Discoveries:
getMediaStream() ONLY works after join()
The stream object is not available until session is joined
Use attachVideo() NOT renderVideo()
renderVideo() is deprecated
attachVideo() returns a VideoPlayer element to append to DOM
See: Video Rendering
The SDK is Event-Driven
You MUST listen for events to render participant videos
key events: peer-video-state-change, user-added, user-removed
See: Event Handling
Peer Videos on Mid-Session Join
Existing participants' videos won't auto-render
Must manually iterate getAllUser() and attachVideo()
See: Video Rendering
CDN vs NPM
CDN exports as
WebVideoSDK.default, notZoomVideoSome networks/ad blockers may block
source.zoom.us- allowlist or use a permitted fallback strategySee: Session Join Pattern
SharedArrayBuffer for HD
Required for 720p/1080p video
Need COOP/COEP headers on server
Check with
stream.isSupportHDVideo()
Screen Share Element Type
Check
isStartShareScreenWithVideoElement()for correct element typeSee: Screen Share
Command Channel Setup Order
Must call getCommandClient() AFTER client.join()
Register listeners AFTER join, not before
Web uses getCommandClient() not getCmdChannel()
See: Command Channel
Command Channel is Session-Scoped
Does NOT span across different sessions
Both sender and receiver must be in the same session
Quick Reference
"getMediaStream() returns undefined"
→ Call AFTER join() completes
"Video not showing"
→ Video Rendering - Use attachVideo(), check events
"renderVideo() doesn't work"
→ Video Rendering - Use attachVideo() instead
"How do I implement [feature]?"
"How do I navigate to [client]?"
"What error code means what?"
Document Version
Based on Zoom Video SDK for Web v2.3.x
Happy coding!
Remember: The SDK Architecture Pattern is your key to unlocking the entire SDK. Read it first!
Operations
RUNBOOK.md - 5-minute preflight and debugging checklist.
Files
- ATTRIBUTION.mdAdded by AutoGineer878 B
- LICENSELicence file added by AutoGineer1.1 KiB
- RUNBOOK.md2.5 KiB
- SKILL.md25.6 KiB
- agents/openai.yaml300 B
- concepts/sdk-architecture-pattern.md8.3 KiB
- concepts/singleton-hierarchy.md18.9 KiB
- examples/chat.md12.0 KiB
- examples/command-channel.md7.1 KiB
- examples/event-handling.md14.1 KiB
- examples/framework-integrations.md10.8 KiB
- examples/react-hooks.md9.8 KiB
- examples/recording.md10.3 KiB
- examples/screen-share.md12.0 KiB
- examples/session-join-pattern.md10.1 KiB
- examples/transcription.md13.9 KiB
- examples/video-rendering.md9.9 KiB
- references/events-reference.md12.8 KiB
- references/web-reference.md15.5 KiB
- references/web.md26.1 KiB
- troubleshooting/common-issues.md10.9 KiB
references/web.md
Video SDK - Web
Build custom video experiences in the browser with Zoom Video SDK.
Overview
The Zoom Video SDK for Web enables fully customized video applications using Zoom's infrastructure. You control the UI, branding, and user experience.
Prerequisites
Video SDK credentials from Marketplace (sign-in required)
SDK Key and Secret
Modern browser (Chrome, Firefox, Safari, Edge)
Installation
NPM (Recommended)
npm install @zoom/videosdkCDN (Fallback Strategy)
Note: Some networks/ad blockers can block
source.zoom.us. Prefer allowlisting the domain in managed environments. If you need a fallback, consider mirroring/self-hosting only if permitted and you can keep versions in sync.
# Download SDK locally
curl "https://source.zoom.us/videosdk/zoom-video-1.12.0.min.js" -o public/js/zoom-video-sdk.min.js<!-- Use local copy instead of CDN -->
<script src="js/zoom-video-sdk.min.js"></script>Note: Remember to update your local copy when new SDK versions are released.
Quick Start
NPM Usage (Bundler)
import ZoomVideo from '@zoom/videosdk';
const client = ZoomVideo.createClient();
await client.init('en-US', 'Global', { patchJsMedia: true });
await client.join(topic, signature, userName, password);
// CRITICAL: getMediaStream() ONLY works AFTER join()
const stream = client.getMediaStream();
await stream.startVideo();
await stream.startAudio();CDN Usage (No Bundler)
// CDN exports as WebVideoSDK, NOT ZoomVideo
// Must use .default property
const ZoomVideo = WebVideoSDK.default;
const client = ZoomVideo.createClient();
await client.init('en-US', 'Global', { patchJsMedia: true });
await client.join(topic, signature, userName, password);
// CRITICAL: getMediaStream() ONLY works AFTER join()
const stream = client.getMediaStream();
await stream.startVideo();
await stream.startAudio();ES Module with CDN (Race Condition)
When using <script type="module"> with CDN, the SDK may not be loaded yet:
function waitForSDK(timeout = 10000) {
return new Promise((resolve, reject) => {
if (typeof WebVideoSDK !== 'undefined') {
resolve();
return;
}
const start = Date.now();
const check = setInterval(() => {
if (typeof WebVideoSDK !== 'undefined') {
clearInterval(check);
resolve();
} else if (Date.now() - start > timeout) {
clearInterval(check);
reject(new Error('SDK failed to load'));
}
}, 100);
});
}
// Usage
await waitForSDK();
const ZoomVideo = WebVideoSDK.default;
const client = ZoomVideo.createClient();SDK Lifecycle (CRITICAL ORDER)
The SDK has a strict lifecycle. Violating it causes silent failures.
1. Create client: client = ZoomVideo.createClient()
2. Initialize: await client.init('en-US', 'Global', options)
3. Join session: await client.join(topic, signature, userName, password)
4. Get stream: stream = client.getMediaStream() ← ONLY AFTER JOIN
5. Start media: await stream.startVideo() / await stream.startAudio()Common Mistake:
// ❌ WRONG: Getting stream before joining
const stream = client.getMediaStream(); // Returns undefined!
await client.join(...);
// ✅ CORRECT: Get stream after joining
await client.join(...);
const stream = client.getMediaStream(); // Works!Video Rendering Best Practices
These show up repeatedly in forum "high CPU", "freezing", and "Safari/Firefox rendering" threads.
Prefer a single rendering pipeline/control rather than one independent renderer per participant.
Add videos incrementally and measure CPU/GPU usage.
Degrade gracefully when
isSupportMultipleVideos()is false (mobile Safari, lower-end devices).Consider lower quality subscriptions for non-active speakers.
Key Features
WebRTC Mode
Enable WebRTC mode for direct peer-to-peer streaming with HD video support:
await client.init('en-US', 'Global', {
patchJsMedia: true,
webrtc: true // Enable WebRTC mode
});Benefits:
Up to 1080p HD video
Improved performance for direct streaming
Virtual Backgrounds
Check support before using:
const stream = client.getMediaStream();
// Always check support first
if (stream.isSupportVirtualBackground()) {
// Blur background
await stream.updateVirtualBackgroundImage('blur');
// Custom image background
await stream.updateVirtualBackgroundImage('https://example.com/bg.jpg');
// Remove virtual background
await stream.updateVirtualBackgroundImage(undefined);
} else {
console.log('Virtual backgrounds not supported on this device');
}HD Video Resolution
Check HD Capability (IMPORTANT)
Always check if HD is supported before enabling:
const stream = client.getMediaStream();
// Check if 720p is supported
const hdSupported = stream.isSupportHDVideo();
console.log('HD (720p) supported:', hdSupported);
// Get maximum video quality (returns VideoQuality enum)
const maxQuality = stream.getVideoMaxQuality();
// 0=90P, 1=180P, 2=360P, 3=720P, 4=1080P
// Check SharedArrayBuffer (required for HD)
const sabAvailable = typeof SharedArrayBuffer === 'function';
if (!sabAvailable) {
console.warn('HD requires SharedArrayBuffer - enable COOP/COEP headers');
}Enable HD Video
// Start video with HD quality (720p)
await stream.startVideo({ hd: true });
// Start video with Full HD (1080p)
await stream.startVideo({ hd: true, fullHd: true });
// Subscribe to specific quality
await stream.attachVideo(userId, VideoQuality.Video_720P);Check Multiple Video Support
// Check if gallery view is possible
const multipleVideosSupported = stream.isSupportMultipleVideos();
// Get max renderable videos
const maxRenderable = stream.getMaxRenderableVideos();
console.log('Can render up to', maxRenderable, 'videos');Complete HD Detection Flow
async function checkHDCapability(client) {
// 1. Check SharedArrayBuffer
const sabAvailable = typeof SharedArrayBuffer === 'function';
// 2. Check system requirements
const compatibility = ZoomVideo.checkSystemRequirements();
// 3. Check feature requirements
const features = ZoomVideo.checkFeatureRequirements();
// 4. After joining, check stream capabilities
const stream = client.getMediaStream();
return {
sharedArrayBuffer: sabAvailable,
videoCompatible: compatibility.video,
hdSupported: stream.isSupportHDVideo(),
maxQuality: stream.getVideoMaxQuality(),
maxRenderable: stream.getMaxRenderableVideos(),
multipleVideos: stream.isSupportMultipleVideos(),
virtualBackground: stream.isSupportVirtualBackground()
};
}Resolution tiers:
1:1 calls: Up to 1080p
Small groups: Up to 720p
Larger sessions: Adaptive
Concurrent HD limits:
Max 2 concurrent 720p subscriptions
Max 1 concurrent 1080p render
Rendering Modes
Multiple rendering options available:
WebRTC mode (direct streaming)
WebAssembly mode (default)
Canvas rendering
Video element rendering
Video Processor (Custom Effects)
The VideoProcessor class allows you to intercept and modify video frames before transmission. Use this for custom overlays, effects, face detection, and more.
How It Works
Create a video processor worker
Extend
VideoProcessorclassImplement
processFrame()to modify each frameOutput to
OffscreenCanvas
Basic Example
// video-processor-worker.js
class MyVideoProcessor extends VideoProcessor {
constructor(port, options) {
super(port, options);
}
processFrame(input, output) {
const ctx = output.getContext('2d');
// Draw original frame
ctx.drawImage(input, 0, 0);
// Add overlay (e.g., text, graphics)
ctx.fillStyle = 'white';
ctx.font = '24px Arial';
ctx.fillText('Live', 20, 40);
return true;
}
}Face Detection with face-api.js
Combine VideoProcessor with face-api.js for face detection overlays:
// video-processor-worker.js
import * as faceapi from 'face-api.js';
class FaceDetectionProcessor extends VideoProcessor {
async processFrame(input, output) {
const ctx = output.getContext('2d');
// Draw original frame
ctx.drawImage(input, 0, 0);
// Detect faces
const detections = await faceapi.detectAllFaces(input);
// Draw bounding boxes
detections.forEach(detection => {
const box = detection.box;
ctx.strokeStyle = '#00ff00';
ctx.lineWidth = 2;
ctx.strokeRect(box.x, box.y, box.width, box.height);
});
return true;
}
}Use Cases
| Use Case | Description |
|---|---|
| Face detection | Bounding boxes, landmarks |
| AR effects | Glasses, hats, masks |
| Beauty filters | Skin smoothing, color correction |
| Overlays | Text, logos, watermarks |
| Real-time translation | OCR + translation overlay |
Resources
VideoProcessor API: https://marketplacefront.zoom.us/sdk/custom/web/classes/VideoProcessor.html
Zoom Blog - AI Text Translation: https://developers.zoom.us/blog/ai-text-translator-with-videosdk-share-processor/
Video Rendering (CRITICAL - Event Driven)
The SDK is event-driven. You must listen for events and render/detach videos accordingly.
Use attachVideo() NOT renderVideo()
renderVideo() is deprecated. Use attachVideo() which returns a VideoPlayer element to append to DOM.
import { VideoQuality } from '@zoom/videosdk';
const stream = client.getMediaStream();
// Start your camera
await stream.startVideo();
// Attach video - returns a VideoPlayer element
const videoElement = await stream.attachVideo(userId, VideoQuality.Video_360P);
// Append to your container
document.getElementById('video-container').appendChild(videoElement);VideoQuality Enum
import { VideoQuality } from '@zoom/videosdk';
VideoQuality.Video_90P // 0
VideoQuality.Video_180P // 1
VideoQuality.Video_360P // 2 (recommended for most cases)
VideoQuality.Video_720P // 3
VideoQuality.Video_1080P // 4Detach Video
// Detach and remove from DOM
const elements = await stream.detachVideo(userId);
if (Array.isArray(elements)) {
elements.forEach(e => e.remove());
} else {
elements.remove();
}Required Events to Listen
You MUST listen to these events to properly render participant videos:
// When another participant's video state changes
client.on('peer-video-state-change', async (payload) => {
const { action, userId } = payload;
if (action === 'Start') {
// Participant turned on video - attach it
const element = await stream.attachVideo(userId, VideoQuality.Video_360P);
container.appendChild(element);
} else if (action === 'Stop') {
// Participant turned off video - detach it
await stream.detachVideo(userId);
}
});
// When participants join/leave
client.on('user-added', (payload) => {
// New participant joined - check if their video is on
const users = client.getAllUser();
// Render videos for users with bVideoOn === true
});
client.on('user-removed', (payload) => {
// Participant left - clean up their video element
const { userId } = payload;
stream.detachVideo(userId);
});
// Participant state updates (mute, video, etc)
client.on('user-updated', (payload) => {
// Re-check participant states
const users = client.getAllUser();
});Participant Properties
const users = client.getAllUser();
users.forEach(user => {
user.userId // Unique user ID
user.displayName // User's display name
user.bVideoOn // Boolean - is video enabled?
user.muted // Boolean - is audio muted?
user.audio // '' | 'computer' | 'phone'
});Complete React Pattern
// When your video turns on
useEffect(() => {
if (isVideoOn && stream && currentUserId) {
const attach = async () => {
const element = await stream.attachVideo(currentUserId, VideoQuality.Video_360P);
containerRef.current?.appendChild(element);
};
attach();
}
}, [isVideoOn, stream, currentUserId]);
// Listen for other participants
useEffect(() => {
if (!client) return;
const handleVideoChange = async (payload) => {
const { action, userId } = payload;
if (action === 'Start') {
const element = await stream.attachVideo(userId, VideoQuality.Video_360P);
// Append to appropriate container
} else {
await stream.detachVideo(userId);
}
};
client.on('peer-video-state-change', handleVideoChange);
return () => client.off('peer-video-state-change', handleVideoChange);
}, [client, stream]);Legacy: renderVideo (Deprecated)
Note:
renderVideo()is deprecated. UseattachVideo()instead.
If you must use canvas rendering:
Canvas Must Exist in DOM
// CORRECT: Canvas exists before rendering
const canvas = document.getElementById('my-canvas'); // Already in DOM
await stream.renderVideo(canvas, userId, 640, 360, 0, 0, 3);
// WRONG: Creating canvas but not adding to DOM
const canvas = document.createElement('canvas');
await stream.renderVideo(canvas, userId); // Won't display!Use Single Rendering Control (IMPORTANT)
For performance, use ONE shared rendering control for all video streams, NOT one control per video.
// CORRECT: Single video container for all participants
const videoContainer = document.getElementById('video-container');
const stream = client.getMediaStream();
// Render all participants to the same container
await stream.renderVideo(videoContainer, userId, width, height, x, y, quality);// WRONG: Creating separate controls per participant
// This degrades performance significantly!
participants.forEach(p => {
const container = document.createElement('div'); // DON'T do this
stream.renderVideo(container, p.id, ...);
});Why:
Multiple rendering controls consume excessive resources
Performance degrades significantly with more participants
Single control handles internal layout management efficiently
Peer Video on Mid-Session Join (IMPORTANT)
Existing participants' videos won't auto-render when you join mid-session.
You must manually iterate all users and attach their video:
import { VideoQuality } from '@zoom/videosdk';
// After joining, render existing participants' videos
const renderExistingVideos = async () => {
await new Promise(resolve => setTimeout(resolve, 500));
const stream = client.getMediaStream();
const users = client.getAllUser();
const currentUserId = client.getCurrentUserInfo().userId;
for (const user of users) {
if (user.bVideoOn && user.userId !== currentUserId) {
const element = await stream.attachVideo(user.userId, VideoQuality.Video_360P);
document.getElementById(`video-${user.userId}`).appendChild(element);
}
}
};Key points:
Check
user.bVideoOnto see if video is enabledSkip self (
client.getCurrentUserInfo().userId)Add ~500ms delay after join before rendering
Use
attachVideo()notrenderVideo()
SharedArrayBuffer
For optimal performance, configure these headers on your server:
Cross-Origin-Opener-Policy: same-origin
Cross-Origin-Embedder-Policy: require-corpNote: As of v1.11.2, SharedArrayBuffer is elective (not strictly required).
Event Handling (CRITICAL)
The SDK is event-driven. You MUST listen for these events:
// Participant joined
client.on('user-added', (payload) => {
console.log('User joined:', payload);
// payload contains user info
});
// Participant left
client.on('user-removed', (payload) => {
console.log('User left:', payload);
// Clean up their video element
stream.detachVideo(payload.userId);
});
// Participant state changed (mute, video, etc)
client.on('user-updated', (payload) => {
console.log('User updated:', payload);
});
// CRITICAL: Other participant's video turned on/off
client.on('peer-video-state-change', async (payload) => {
const { action, userId } = payload;
// action: 'Start' | 'Stop'
if (action === 'Start') {
const element = await stream.attachVideo(userId, VideoQuality.Video_360P);
// Append element to container
} else {
await stream.detachVideo(userId);
}
});
// Connection state changed
client.on('connection-change', (payload) => {
// payload.state: 'Connected' | 'Closed' | 'Reconnecting' | etc
});Event Cleanup
Always remove listeners when component unmounts:
// React pattern
useEffect(() => {
const handler = (payload) => { /* ... */ };
client.on('peer-video-state-change', handler);
return () => {
client.off('peer-video-state-change', handler);
};
}, [client]);Common Tasks
Start/Stop Video
await stream.startVideo();
await stream.stopVideo();Start/Stop Audio
await stream.startAudio();
await stream.muteAudio();
await stream.unmuteAudio();Screen Sharing
Receive Screen Share
Listen to active-share-change event and render when active:
client.on('active-share-change', async (payload) => {
const stream = client.getMediaStream();
if (payload.state === 'Active') {
// Add small delay to ensure DOM element exists
await new Promise(resolve => setTimeout(resolve, 100));
// Check if should use video element or canvas
if (stream.isStartShareScreenWithVideoElement()) {
const video = document.getElementById('share-video');
await stream.startShareView(video as unknown as HTMLCanvasElement, payload.userId);
} else {
const canvas = document.getElementById('share-canvas');
await stream.startShareView(canvas, payload.userId);
}
} else if (payload.state === 'Inactive') {
await stream.stopShareView();
}
});Send Screen Share
Check rendering mode before starting:
const stream = client.getMediaStream();
// Check which element type to use
if (stream.isStartShareScreenWithVideoElement()) {
// Use video element
const video = document.getElementById('share-video');
await stream.startShareScreen(video as unknown as HTMLCanvasElement);
} else {
// Use canvas element
const canvas = document.getElementById('share-canvas');
await stream.startShareScreen(canvas);
}Stop Screen Share
await stream.stopShareScreen();Type Casting Workaround
SDK types expect HTMLCanvasElement even for video elements. Cast when needed:
// When using HTMLVideoElement where SDK expects HTMLCanvasElement
const video = document.getElementById('share-video') as HTMLVideoElement;
await stream.startShareView(video as unknown as HTMLCanvasElement, userId);Host vs Participant
// Leave session (others stay)
await client.leave();
// End session for ALL participants (host only)
await client.leave(true);Chat Implementation
Initialize Chat
const chatClient = client.getChatClient();
// Wait for chat to be ready
chatClient.on('chat-on', () => {
console.log('Chat is ready');
});Send Message
// Send to everyone
await chatClient.send('Hello, everyone!');
// Send to specific user
await chatClient.sendToUser(userId, 'Private message');Receive Messages
chatClient.on('chat-on-message', (payload) => {
const { message, sender, timestamp } = payload;
console.log(`${sender.name}: ${message}`);
});Error Handling
Common Join Errors
| Error | Cause | Solution |
|---|---|---|
Invalid signature | JWT expired or malformed | Generate new signature |
Session does not exist | Host hasn't started yet | Show "waiting" message, retry |
Permission denied | User denied camera/mic | Request permission again |
Example Error Handler
try {
await client.join(topic, signature, userName, password);
} catch (error) {
if (error.reason?.includes('signature')) {
// Regenerate signature and retry
} else if (error.reason?.includes('Session')) {
// Show "Waiting for host..." and poll
} else if (error.reason?.includes('Permission')) {
// Guide user to enable permissions
}
console.error('Join failed:', error);
}Recording (Host Only)
Only the host (role=1) can start/stop recording:
const recordingClient = client.getRecordingClient();
// Start cloud recording
await recordingClient.startCloudRecording();
// Stop recording
await recordingClient.stopCloudRecording();
// Listen for recording status changes
client.on('recording-change', (payload) => {
console.log('Recording status:', payload.status);
});Live Transcription
const transcriptionClient = client.getLiveTranscriptionClient();
// Start live transcription
await transcriptionClient.startLiveTranscription();
// Stop live transcription
await transcriptionClient.stopLiveTranscription();
// Listen for captions
client.on('caption-message', (payload) => {
console.log(`${payload.displayName}: ${payload.text}`);
});Device Selection
// Get available devices
const devices = await ZoomVideo.getDevices();
console.log('Cameras:', devices.cameras);
console.log('Microphones:', devices.microphones);
console.log('Speakers:', devices.speakers);
// Get currently active devices
const stream = client.getMediaStream();
const activeCamera = stream.getActiveCamera();
const activeMic = stream.getActiveMicrophone();
const activeSpeaker = stream.getActiveSpeaker();
// Switch devices
await stream.switchCamera(deviceId);
await stream.switchMicrophone(deviceId);
await stream.switchSpeaker(deviceId);Network Quality
Monitor network quality in real-time:
client.on('network-quality-change', (payload) => {
// payload.type = 'uplink' or 'downlink'
// payload.level = 0-5 (5 is best)
if (payload.level < 2) {
console.warn(`Poor ${payload.type} network quality: ${payload.level}`);
}
});File Sharing
const chatClient = client.getChatClient();
// Send file to everyone (receiverId = 0)
await chatClient.sendFile(file, 0);
// Send file to specific user
await chatClient.sendFile(file, userId);Breakout Rooms (Subsessions)
Video SDK uses "Subsessions" instead of native breakout rooms:
const subsessionClient = client.getSubsessionClient();
// Create subsessions
const roomNames = ['Room 1', 'Room 2', 'Room 3'];
await subsessionClient.createSubsessions(roomNames);
// Open subsessions
const rooms = subsessionClient.getSubsessionList();
await subsessionClient.openSubsessions(rooms);
// Broadcast message to all rooms
await subsessionClient.broadcast('Please return to main session in 5 minutes');
// Close all subsessions
await subsessionClient.closeAllSubsessions();Reactions via Command Channel
Use the command channel for custom messages like reactions:
const commandClient = client.getCommandClient();
// Send reaction
const reaction = { type: 'reaction', emoji: '👍' };
await commandClient.send(JSON.stringify(reaction));
// Receive reactions
client.on('command-channel-message', (payload) => {
try {
const data = JSON.parse(payload.text);
if (data.type === 'reaction') {
console.log(`${payload.senderName} reacted with ${data.emoji}`);
}
} catch (e) {
console.log('Non-JSON message:', payload.text);
}
});CORS Errors (Telemetry)
CORS errors to log-external-gateway.zoom.us are harmless.
These are caused by COOP/COEP headers blocking telemetry requests. They don't affect SDK functionality.
// These console errors can be safely ignored:
// Access to fetch at 'https://log-external-gateway.zoom.us/...' has been blocked by CORS policyResources
Official docs: https://developers.zoom.us/docs/video-sdk/web/
API Reference: https://marketplacefront.zoom.us/sdk/custom/web/modules.html
Sample app: https://github.com/zoom/videosdk-web-sample
Host Participant Management
const stream = client.getMediaStream();
// Mute all participants
await stream.muteAllAudio();
// Mute/unmute specific participant
await stream.muteAudio(userId);
await stream.unmuteAudio(userId);
// Remove participant (host only)
await client.removeUser(userId);
// Transfer host
await client.makeHost(userId);
// Make co-host
await client.makeManager(userId);Mirror Self View
const stream = client.getMediaStream();
// Toggle mirror (useful for self-view)
await stream.mirrorVideo(true); // Enable mirror
await stream.mirrorVideo(false); // Disable mirrorShare Screen with Audio
const stream = client.getMediaStream();
const shareElement = document.getElementById('share-element');
// Share with system audio
await stream.startShareScreen(shareElement, {
secondaryAudio: true
});Troubleshooting
"ZoomVideo is not defined" / "WebVideoSDK is not defined"
Causes:
Ad blocker blocking
source.zoom.usCDNES module loading before SDK script
Solutions:
Allowlist
source.zoom.usin your environment, or use a permitted fallback (mirror/self-host) if you can keep versions in syncUse
waitForSDK()function for ES modules
Camera/Microphone Not Working
Causes:
Browser permission denied
Device in use by another app
No hardware available
Solutions:
Check browser permissions (Settings → Privacy → Camera/Microphone)
Close other apps using the device
Try different browser
Video Not Displaying (Silent Failure)
Cause: Called getMediaStream() before join() completed
Solution: Follow the SDK lifecycle order exactly (see SDK Lifecycle section)
CORS Error on Signature Endpoint
Cause: Frontend (HTTPS) calling backend (HTTP) or different origin
Solutions:
Use nginx proxy to same origin (recommended)
Configure CORS on backend with explicit origins
Ensure both frontend and backend use HTTPS
Browser Compatibility
| Feature | Chrome | Firefox | Safari | Edge |
|---|---|---|---|---|
| Video | ✅ 80+ | ✅ 75+ | ✅ 14+ | ✅ 80+ |
| Audio | ✅ 80+ | ✅ 75+ | ✅ 14+ | ✅ 80+ |
| Screen Share | ✅ 80+ | ✅ 75+ | ⚠️ 15+ | ✅ 80+ |
| Virtual BG | ✅ 80+ | ✅ 90+ | ❌ | ✅ 80+ |
Safari Notes:
Virtual background not supported
Screen sharing requires macOS 15+
Requirements and compatibility
Written for: OpenAI Codex
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Needs: Needs network access, Needs Node.js
Security
No issues found by our static scan· No issues found
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Created by
- Zoom
- Publisher
- OpenAI (Official)
- Distributed by
- OpenAI
- Source
- openai/plugins · plugins/zoom/skills/video-sdk/web · commit d420d13
- Licence
- MIT License (redistribution allowed)
- LICENSE (added by AutoGineer from plugins/zoom/LICENSE)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Zoom or OpenAI.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download zoom-video-sdk-web.zip