Zoom General
AnthropicOfficialCreated by ZoomDistributed by Anthropic
- Skill
- Meta (authoring, orchestration, planning, memory)
- Agent tooling
- MIT
- Medium risk
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The zoom-general skill serves as the primary entry point and classification layer for developers working with the Zoom platform. It provides a structured framework to identify the correct Zoom product, SDK, or API path based on user intent. It includes logic for routing complex queries, chaining multiple skills (such as combining REST APIs with OAuth and webhooks), and resolving ambiguities between deterministic automation and AI-driven agentic workflows.
What it does
- Classifies developer queries to identify the appropriate Zoom product or SDK.
- Provides a routing matrix to distinguish between REST API, MCP, and SDK use cases.
- Offers guidance on choosing the correct Zoom app type (General, S2S, or Webhook-only).
- Facilitates skill chaining for multi-step integrations like OAuth and webhook setups.
- Provides decision frameworks for API vs. MCP and SDK vs. REST implementation paths.
- Acts as a central index for all specialized Zoom developer skills.
When to use it
- When you are unsure which Zoom SDK or API is required for your project.
- When you need to determine if your task requires REST APIs, MCP tools, or a hybrid approach.
- When planning a complex integration that involves authentication, webhooks, and API orchestration.
- When you need to compare different Zoom app types to match your architectural requirements.
- When you need to resolve ambiguity between similar Zoom products like Meeting SDK and Video SDK.
Advantages
- Reduces development friction by directing users to the most relevant documentation and skills.
- Ensures architectural consistency by enforcing standard routing patterns.
- Simplifies complex decision-making through clear matrices and guardrails.
- Promotes best practices for authentication and event-driven design.
- Provides a unified entry point for navigating the entire Zoom developer ecosystem.
Usage examples
- “I want to build a custom video UI for a Zoom meeting on the web, what should I use?”
- The skill identifies the requirement for a custom UI around a real meeting and routes the user to the zoom-meeting-sdk-web-component-view skill.
- “Should I use the REST API or MCP for my AI agent?”
- The skill provides the API vs. MCP routing matrix, explaining that REST is for deterministic automation while MCP is for dynamic AI tool orchestration.
- “How do I set up a server-side integration that handles meetings and webhooks?”
- The skill suggests the Rivet SDK for scaffolding or chains the zoom-rest-api, zoom-oauth, and zoom-webhooks skills.
Install
Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/anthropics/zoom-general/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip zoom-general.zip -d .agents/skills
Documentation by Zoom
Zoom General (Cross-Product Skills)
Background reference for cross-product Zoom questions. Prefer the workflow skills first, then use this file for shared platform guidance and routing detail.
How zoom-general Routes a Complex Developer Query
Use zoom-general as the classifier and chaining layer:
detect product signals in the query
pick one primary skill
attach secondary skills for auth, events, or deployment edges
ask one short clarifier only when two routes match with similar confidence
Minimal implementation:
type SkillId =
| 'zoom-general'
| 'zoom-rest-api'
| 'zoom-webhooks'
| 'zoom-oauth'
| 'zoom-meeting-sdk-web-component-view'
| 'zoom-video-sdk'
| 'zoom-mcp';
const hasAny = (q: string, words: string[]) => words.some((w) => q.includes(w));
function detectSignals(rawQuery: string) {
const q = rawQuery.toLowerCase();
return {
meetingCustomUi: hasAny(q, ['zoom meeting', 'custom ui', 'component view', 'embed meeting']),
customVideo: hasAny(q, ['video sdk', 'custom video session', 'peer-video-state-change']),
restApi: hasAny(q, ['rest api', '/v2/', 'create meeting', 'list users', 's2s oauth']),
webhooks: hasAny(q, ['webhook', 'x-zm-signature', 'event subscription', 'crc']),
oauth: hasAny(q, ['oauth', 'pkce', 'token refresh', 'account_credentials']),
mcp: hasAny(q, ['zoom mcp', 'agentic retrieval', 'tools/list', 'semantic meeting search']),
};
}
function pickPrimarySkill(s: ReturnType<typeof detectSignals>): SkillId {
if (s.meetingCustomUi) return 'zoom-meeting-sdk-web-component-view';
if (s.mcp) return 'zoom-mcp';
if (s.restApi) return 'zoom-rest-api';
if (s.customVideo) return 'zoom-video-sdk';
return 'zoom-general';
}
function buildChain(primary: SkillId, s: ReturnType<typeof detectSignals>): SkillId[] {
const chain = [primary];
if (s.oauth && !chain.includes('zoom-oauth')) chain.push('zoom-oauth');
if (s.webhooks && !chain.includes('zoom-webhooks')) chain.push('zoom-webhooks');
return chain;
}Example:
Create a meeting, configure webhooks, and handle OAuth token refresh->zoom-rest-api -> zoom-oauth -> zoom-webhooksBuild a custom video UI for a Zoom meeting on web->zoom-meeting-sdk-web-component-view
For the full TypeScript implementation and handoff contract, use references/routing-implementation.md.
Choose Your Path
| I want to... | Use this skill |
|---|---|
| Build a custom web UI around a real Zoom meeting | zoom-meeting-sdk-web-component-view |
| Build deterministic automation/configuration/reporting with explicit request control | zoom-rest-api |
| Receive event notifications (HTTP push) | zoom-webhooks |
| Receive event notifications (WebSocket, low-latency) | zoom-websockets |
| Embed Zoom meetings in my app | zoom-meeting-sdk |
| Build custom video experiences (Web, React Native, Flutter, Android, iOS, macOS, Unity, Linux) | zoom-video-sdk |
| Build an app that runs inside Zoom client | zoom-apps-sdk |
| Transcribe uploaded or stored media with AI Services Scribe | scribe |
| Access live audio/video/transcripts from meetings | zoom-rtms |
| Enable collaborative browsing for support | zoom-cobrowse-sdk |
| Build Contact Center apps and channel integrations | contact-center |
| Build Virtual Agent web/mobile chatbot experiences | virtual-agent |
| Build Zoom Phone integrations (Smart Embed, Phone API, webhooks, URI flows) | phone |
| Build Team Chat apps and integrations | zoom-team-chat |
| Build server-side integrations with Rivet (auth + webhooks + APIs) | rivet-sdk |
| Run browser/device/network preflight diagnostics before join | probe-sdk |
| Add pre-built UI components for Video SDK | zoom-ui-toolkit |
| Implement OAuth authentication (all grant types) | zoom-oauth |
| Build AI-driven tool workflows (AI Companion/agents) over Zoom data | zoom-mcp |
| Build AI-driven Whiteboard workflows over Zoom Whiteboard MCP | zoom-mcp/whiteboard |
| Build enterprise AI systems with stable API core + AI tool layer | zoom-rest-api + zoom-mcp |
Planning Checkpoint: Rivet SDK (Optional)
When a user starts planning a server-side integration that combines auth + webhooks + API calls, ask this first:
Rivet SDK is a Node.js framework that bundles Zoom auth handling, webhook receivers, and typed API wrappers.Do you want to use Rivet SDK for faster scaffolding, or do you prefer a direct OAuth + REST implementation without Rivet?
Routing after answer:
If user chooses Rivet: chain
rivet-sdk+oauth+rest-api.If user declines Rivet: chain
oauth+rest-api(+webhooksor product skill as needed).
SDK vs REST Routing Matrix (Hard Stop)
| User intent | Correct path | Do not route to |
|---|---|---|
| Embed Zoom meeting in app UI | zoom-meeting-sdk | REST-only join_url flow |
| Build custom web UI for a real Zoom meeting | zoom-meeting-sdk-web-component-view | zoom-video-sdk |
| Build custom video UI/session app | zoom-video-sdk | Meeting SDK or REST meeting links |
| Get browser join links / manage meeting resources | zoom-rest-api | Meeting SDK join implementation |
Routing guardrails:
If user asks for SDK embed/join behavior, stay in SDK path.
If the prompt says meeting plus custom UI/video/layout/embed, prefer
zoom-meeting-sdk-web-component-view.Only use
zoom-video-sdkwhen the user is building a custom session product rather than a Zoom meeting.Only use REST path for resource management, reporting, or link distribution unless user explicitly requests a mixed architecture.
For executable classification/chaining logic and error handling, see references/routing-implementation.md.
API vs MCP Routing Matrix (Hard Stop)
| User intent | Correct path | Why |
|---|---|---|
| Deterministic backend automation, account/user configuration, reporting, scheduled jobs | zoom-rest-api | Explicit request/response control and repeatable behavior |
| AI agent chooses tools dynamically, cross-platform AI tool interoperability | zoom-mcp | MCP is optimized for dynamic tool discovery and agentic workflows |
| Enterprise AI architecture (stable core + adaptive AI layer) | zoom-rest-api + zoom-mcp | APIs run core system actions; MCP exposes curated AI tools/context |
Routing guardrails:
Do not replace deterministic backend APIs with MCP-only routing.
Do not force raw REST-first routing when the task is AI-agent tool orchestration.
Prefer hybrid routing when the user needs both stable automation and AI-driven interactions.
MCP remote server works over Streamable HTTP/SSE; use this path when the target client/agent supports MCP transports (for example Claude or VS Code).
Do not design per-tenant custom MCP endpoint provisioning; Zoom MCP endpoints are shared at instance/cluster level.
Source: https://developers.zoom.us/docs/mcp/library/resources/apis-vs-mcp/
Ambiguity Resolution (Ask Before Routing)
When a prompt matches both API and MCP paths with similar confidence, ask one short clarifier before execution:
Do you want deterministic REST API automation, AI-agent MCP tooling, or a hybrid of both?
Then route as:
REST answer →
zoom-rest-apiMCP answer →
zoom-mcpHybrid answer →
zoom-rest-api + zoom-mcp
MCP Availability and Topology Notes
Zoom-hosted MCP access is evolving; docs indicate a model where Zoom exposes product-scoped MCP servers (for example Meetings, Team Chat, Whiteboard).
Use
zoom-mcpas the parent MCP entry point.Route Whiteboard-specific MCP requests to zoom-mcp/whiteboard.
When a request is product-specific and MCP coverage exists, route to that MCP product surface first; otherwise use REST/SDK skills for deterministic implementation.
Webhooks vs WebSockets
Both receive event notifications, but differ in approach:
| Aspect | webhooks | zoom-websockets |
|---|---|---|
| Connection | HTTP POST to your endpoint | Persistent WebSocket |
| Latency | Higher | Lower |
| Security | Requires public endpoint | No exposed endpoint |
| Setup | Simpler | More complex |
| Best for | Most use cases | Real-time, security-sensitive |
Common Use Cases
| Use Case | Description | Skills Needed |
|---|---|---|
| Meeting + Webhooks + OAuth Refresh | Create a meeting, process real-time updates, and refresh OAuth tokens safely in one design | zoom-rest-api + zoom-oauth + zoom-webhooks |
| Scribe Transcription Pipeline | Transcribe uploaded files or S3 archives with AI Services Scribe using fast mode or batch jobs | scribe + optional zoom-rest-api + optional zoom-webhooks |
| APIs vs MCP Routing | Decide whether to route to deterministic Zoom APIs, AI-driven MCP, or a hybrid design | zoom-rest-api and/or zoom-mcp |
| Custom Meeting UI (Web) | Build a custom video UI for a real Zoom meeting in a web app using Meeting SDK Component View | zoom-meeting-sdk-web-component-view + zoom-oauth |
| Meeting Automation | Schedule, update, delete meetings programmatically | zoom-rest-api |
| Meeting Bots | Build bots that join meetings for AI/transcription/recording | meeting-sdk/linux + zoom-rest-api + optional zoom-webhooks |
| High-Volume Meeting Platform | Design distributed meeting creation and event processing with retries, queues, and reconciliation | zoom-rest-api + zoom-webhooks + zoom-oauth |
| Recording & Transcription | Download recordings, get transcripts | zoom-webhooks + zoom-rest-api |
| Recording Download Pipeline | Auto-download recordings to your own storage (S3, GCS, etc.) | zoom-webhooks + zoom-rest-api |
| Real-Time Media Streams | Access live audio, video, transcripts via WebSocket | zoom-rtms + zoom-webhooks |
| In-Meeting Apps | Build apps that run inside Zoom meetings | zoom-apps-sdk + zoom-oauth |
| React Native Meeting Embed | Embed meetings into iOS/Android React Native apps | zoom-meeting-sdk-react-native + zoom-oauth |
| Native Meeting SDK Multi-Platform Delivery | Align Android, iOS, macOS, and Unreal Meeting SDK implementations under one auth/version strategy | zoom-meeting-sdk + platform skills |
| Native Video SDK Multi-Platform Delivery | Align Android, iOS, macOS, and Unity Video SDK implementations under one auth/version strategy | zoom-video-sdk + platform skills |
| Electron Meeting Embed | Embed meetings into desktop Electron apps | zoom-meeting-sdk-electron + zoom-oauth |
| Flutter Video Sessions | Build custom mobile video sessions in Flutter | zoom-video-sdk-flutter + zoom-oauth |
| React Native Video Sessions | Build custom mobile video sessions in React Native | zoom-video-sdk-react-native + zoom-oauth |
| Immersive Experiences | Custom video layouts with Layers API | zoom-apps-sdk |
| Collaborative Apps | Real-time shared state in meetings | zoom-apps-sdk |
| Contact Center App Lifecycle and Context Switching | Build Contact Center apps that handle engagement events and multi-engagement state | contact-center + zoom-apps-sdk |
| Virtual Agent Campaign Web and Mobile Wrapper | Deliver one campaign-driven bot flow across web and native mobile wrappers | virtual-agent + contact-center |
| Virtual Agent Knowledge Base Sync Pipeline | Sync external knowledge content into Zoom Virtual Agent using web sync or custom API connectors | virtual-agent + zoom-rest-api + zoom-oauth |
| Zoom Phone Smart Embed CRM Integration | Build CRM dialer and call logging flows using Smart Embed plus Phone APIs | phone + zoom-oauth + zoom-webhooks |
| Rivet Event-Driven API Orchestrator | Build a Node.js backend that combines webhooks and API actions through Rivet module clients | rivet-sdk + zoom-oauth + zoom-rest-api |
| Probe SDK Preflight Readiness Gate | Add browser/device/network diagnostics and readiness policy before Meeting SDK or Video SDK joins | probe-sdk + zoom-meeting-sdk or zoom-video-sdk |
Complete Use-Case Index
APIs vs MCP Routing: choose API-only, MCP-only, or hybrid routing using official Zoom criteria.
AI Companion Integration: connect Zoom AI Companion capabilities into your app workflow.
AI Integration: add summarization, transcription, or assistant logic using Zoom data surfaces.
Backend Automation (S2S OAuth): run server-side jobs with account-level OAuth credentials.
Collaborative Apps: build shared in-meeting app state and interactions.
Contact Center Integration: connect Zoom Contact Center signals into external systems.
Contact Center App Lifecycle and Context Switching: implement event-driven engagement state and safe context switching in Contact Center apps.
Virtual Agent Campaign Web and Mobile Wrapper: deploy campaign-based Virtual Agent chat across website and Android/iOS WebView wrappers.
Virtual Agent Knowledge Base Sync Pipeline: automate knowledge-base ingestion with web sync strategy or custom API connector.
Zoom Phone Smart Embed CRM Integration: integrate Smart Embed events, Phone APIs, and CRM workflows with migration-safe data handling.
Rivet Event-Driven API Orchestrator: build a Node.js backend that combines webhook handling and API orchestration with Rivet.
Probe SDK Preflight Readiness Gate: run browser/device/network diagnostics before launching meeting or video session workflows.
Custom Video: decide between Video SDK and related components for custom session UX.
Custom Meeting UI (Web): use Meeting SDK Component View for a custom UI around a real Zoom meeting.
Scribe Transcription Pipeline: use AI Services Scribe for on-demand file transcription and batch archive processing.
Video SDK Bring Your Own Storage: configure Video SDK cloud recordings to write directly to your own S3 bucket.
Customer Support Cobrowsing: implement customer-agent collaborative browsing support flows.
Embed Meetings: embed Zoom meeting experience into your app.
Form Completion Assistant: build guided flows for form filling and completion assistance.
HD Video Resolution: enable and troubleshoot high-definition video requirements.
High-Volume Meeting Platform: build distributed meeting creation and event processing with concrete fallback patterns.
Immersive Experiences: use Zoom Apps Layers APIs for custom in-meeting visuals.
In-Meeting Apps: build Zoom Apps that run directly inside meeting and webinar contexts.
Marketplace Publishing: prepare and ship a Zoom app through Marketplace review.
Meeting Automation: create, update, and manage meetings programmatically.
Meeting Bots: build bots for meeting join, capture, and real-time analysis.
Native Meeting SDK Multi-Platform Delivery: standardize Android, iOS, macOS, and Unreal Meeting SDK delivery with shared auth and version controls.
Native Video SDK Multi-Platform Delivery: standardize Android, iOS, macOS, and Unity Video SDK delivery with shared auth and version controls.
Meeting Details with Events: combine REST retrieval with webhook event streams.
Minutes Calculation: compute usage and minute metrics across meetings/sessions.
Prebuilt Video UI: use UI Toolkit for faster Video SDK-based UI delivery.
QSS Monitoring: monitor Zoom quality statistics and performance indicators.
Raw Recording: capture raw streams for custom recording and processing pipelines.
Electron Meeting Embed: embed meetings in an Electron desktop application.
Flutter Video Sessions: build Video SDK sessions in Flutter mobile apps.
React Native Meeting Embed: embed Meeting SDK into React Native apps.
React Native Video Sessions: build custom video sessions in React Native.
Real-Time Media Streams: consume live media/transcript streams via RTMS.
Recording Download Pipeline: automate recording retrieval and storage pipelines.
Recording & Transcription: manage post-meeting recordings and transcript workflows.
Retrieve Meeting and Subscribe Events: join REST meeting fetch with event subscriptions.
SaaS App OAuth Integration: implement user-level OAuth in multi-tenant SaaS apps.
SDK Size Optimization: reduce bundle/runtime footprint for SDK-based apps.
SDK Wrappers and GUI: evaluate wrapper patterns and GUI frameworks around SDKs.
Team Chat LLM Bot: build a Team Chat bot with LLM-powered responses.
Testing and Development: local testing patterns, mocks, and safe development loops.
Token and Scope Troubleshooting: debug OAuth scope and token mismatch issues.
Transcription Bot (Linux): run Linux meeting bots for live transcription workloads.
Usage Reporting and Analytics: collect and analyze usage/reporting data.
User and Meeting Creation: provision users and schedule meetings in one flow.
Web SDK Embedding: embed meeting experiences in browser-based web apps.
Server-to-Server OAuth with Webhooks: combine account OAuth with event-driven backend processing.
Meeting Links vs Embedding: choose between
join_urldistribution and SDK embedding.Enterprise App Deployment: deploy, govern, and operate Zoom integrations at enterprise scale.
Prerequisites
Zoom account (Pro, Business, or Enterprise)
App created in Zoom App Marketplace
OAuth credentials (Client ID and Secret)
References
Quick Start
Go to marketplace.zoom.us
Click Develop → Build App
Select app type (see references/app-types.md)
Configure OAuth and scopes
Copy credentials to your application
Detailed References
references/authentication.md - OAuth 2.0, S2S OAuth, JWT patterns
references/app-types.md - Decision guide for app types
references/scopes.md - OAuth scopes reference
references/marketplace.md - Marketplace portal navigation
references/query-routing-playbook.md - Route complex queries to the right specialized skills
references/interview-answer-routing.md - Short interview-ready answer pattern for zoom-general routing
references/routing-implementation.md - Concrete TypeScript query classification and skill handoff contract
references/automatic-skill-chaining-rest-webhooks.md - Executable process for REST + webhook chained workflows
references/meeting-webhooks-oauth-refresh-orchestration.md - Concrete design for meeting creation + webhook updates + OAuth token refresh
references/distributed-meeting-fallback-architecture.md - High-volume distributed architecture with retries, circuit breakers, and reconciliation fallbacks
references/community-repos.md - Curated official Zoom sample repositories by product
SDK Maintenance
references/sdk-upgrade-guide.md - Version policy, upgrade steps
references/sdk-upgrade-workflow.md - Changelog + RSS, version-by-version reusable upgrade workflow
references/sdk-logs-troubleshooting.md - Collecting SDK logs
Resources
Official docs: https://developers.zoom.us/
Marketplace: https://marketplace.zoom.us/
Developer forum: https://devforum.zoom.us/
Environment Variables
See references/environment-variables.md for standardized
.envkeys and where to find each value.
Operations
RUNBOOK.md - 5-minute preflight and debugging checklist.
Files
- ATTRIBUTION.mdAdded by AutoGineer975 B
- LICENSELicence file added by AutoGineer1.1 KiB
- RUNBOOK.md2.4 KiB
- SKILL.md25.3 KiB
- references/app-types.md2.6 KiB
- references/authentication.md2.0 KiB
- references/authorization-patterns.md21.3 KiB
- references/automatic-skill-chaining-rest-webhooks.md5.5 KiB
- references/community-repos.md9.3 KiB
- references/distributed-meeting-fallback-architecture.md14.0 KiB
- references/environment-variables.md3.0 KiB
- references/interview-answer-routing.md797 B
- references/known-limitations.md2.5 KiB
- references/marketplace.md1.6 KiB
- references/meeting-webhooks-oauth-refresh-orchestration.md5.3 KiB
- references/query-routing-playbook.md2.7 KiB
- references/routing-implementation.md8.7 KiB
- references/scopes.md3.4 KiB
- references/sdk-logs-troubleshooting.md5.7 KiB
- references/sdk-upgrade-guide.md4.1 KiB
- references/sdk-upgrade-workflow.md3.5 KiB
- use-cases/ai-companion-integration.md10.0 KiB
- use-cases/ai-integration.md7.2 KiB
- use-cases/apis-vs-mcp-routing.md3.5 KiB
- use-cases/backend-automation-s2s-oauth.md5.0 KiB
- use-cases/collaborative-apps.md2.6 KiB
- use-cases/contact-center-app-lifecycle-and-context-switching.md1.2 KiB
- use-cases/contact-center-integration.md1.1 KiB
- use-cases/custom-meeting-ui-web.md2.8 KiB
- use-cases/custom-video.md5.6 KiB
- use-cases/customer-support-cobrowsing.md12.6 KiB
- use-cases/electron-meeting-embed.md1020 B
- use-cases/embed-meetings.md4.9 KiB
- use-cases/enterprise-app-deployment.md1.0 KiB
- use-cases/flutter-video-sessions.md910 B
- use-cases/form-completion-assistant.md15.4 KiB
- use-cases/hd-video-resolution.md8.8 KiB
- use-cases/high-volume-meeting-platform.md1.9 KiB
- use-cases/immersive-experiences.md2.9 KiB
- use-cases/in-meeting-apps.md7.5 KiB
- use-cases/marketplace-publishing.md9.2 KiB
- use-cases/meeting-automation.md6.3 KiB
- use-cases/meeting-bots.md10.6 KiB
- use-cases/meeting-details-with-events.md20.9 KiB
- use-cases/meeting-links-vs-embedding.md989 B
- use-cases/minutes-calculation.md22.6 KiB
- use-cases/native-meeting-sdk-multi-platform.md1.5 KiB
- use-cases/native-video-sdk-multi-platform.md1.2 KiB
- use-cases/prebuilt-video-ui.md12.4 KiB
- use-cases/probe-sdk-preflight-readiness-gate.md1.2 KiB
- use-cases/qss-monitoring.md2.7 KiB
- use-cases/raw-recording.md5.1 KiB
- use-cases/react-native-meeting-embed.md1.0 KiB
- use-cases/react-native-video-sessions.md953 B
- use-cases/real-time-media-streams.md5.5 KiB
- use-cases/recording-download-pipeline.md8.8 KiB
- use-cases/recording-transcription.md7.6 KiB
- use-cases/retrieve-meeting-and-subscribe-events.md33.1 KiB
- use-cases/rivet-event-driven-api-orchestrator.md1.3 KiB
- use-cases/saas-app-oauth-integration.md4.8 KiB
- use-cases/scribe-transcription-pipeline.md1.8 KiB
- use-cases/sdk-size-optimization.md5.0 KiB
- use-cases/sdk-wrappers-gui.md18.6 KiB
- use-cases/server-to-server-oauth-with-webhooks.md1.7 KiB
- use-cases/team-chat-llm-bot.md6.9 KiB
- use-cases/testing-development.md7.2 KiB
- use-cases/token-and-scope-troubleshooting.md2.4 KiB
- use-cases/transcription-bot-linux.md14.5 KiB
- use-cases/usage-reporting-analytics.md8.6 KiB
- use-cases/user-and-meeting-creation.md17.0 KiB
- use-cases/video-sdk-bring-your-own-storage.md6.9 KiB
- use-cases/virtual-agent-campaign-web-mobile-wrapper.md1.4 KiB
- use-cases/virtual-agent-knowledge-base-sync-pipeline.md1.1 KiB
- use-cases/web-sdk-embedding.md4.5 KiB
- use-cases/zoom-phone-smart-embed-crm.md876 B
use-cases/transcription-bot-linux.md
Transcription Bot (Linux)
Build a production-ready transcription bot using Meeting SDK for Linux to automatically transcribe Zoom meetings.
Overview
A transcription bot joins Zoom meetings as a visible participant, captures raw audio, and streams it to a transcription service (AssemblyAI, Whisper, etc.) for real-time or post-meeting transcription.
Skills Needed
meeting-sdk/linux - Primary (headless meeting bot)
zoom-rest-api - Get meeting details, OBF tokens
zoom-oauth - JWT token generation for SDK auth
Architecture
┌──────────────┐ ┌─────────────────┐ ┌──────────────────┐ ┌──────────────┐
│ Meeting │───▶│ Meeting SDK Bot │───▶│ Raw Audio │───▶│ Transcription│
│ Started │ │ (Linux/Docker) │ │ Stream (PCM) │ │ Service │
│ │ │ │ │ 32kHz, 16-bit │ │ (AssemblyAI) │
└──────────────┘ └─────────────────┘ └──────────────────┘ └──────────────┘
│ │ │
▼ ▼ ▼
┌─────────────────┐ ┌──────────────────┐ ┌──────────────┐
│ 1. Get OBF Token│ │ 2. StartRaw │ │ 3. Store │
│ (REST API) │ │ Recording │ │ Transcript│
└─────────────────┘ └──────────────────┘ └──────────────┘Implementation Steps
Step 1: Generate JWT & OBF Tokens
JWT Token (SDK authentication):
# Using zoom-oauth skill
curl -X POST https://your-auth-service.com/generate-jwt \
-d '{"client_id": "YOUR_CLIENT_ID", "client_secret": "YOUR_CLIENT_SECRET"}'OBF Token (join external meetings):
# Via REST API
curl -X POST "https://api.zoom.us/v2/users/{userId}/token?type=obf&ttl=7200" \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN"See: zoom-oauth, bot-authentication
Step 2: Initialize Meeting SDK
Full implementation: meeting-sdk/linux
#include "zoom_sdk.h"
#include <glib.h>
USING_ZOOM_SDK_NAMESPACE
// Initialize SDK
InitParam init_params;
init_params.strWebDomain = "https://zoom.us";
init_params.enableLogByDefault = true;
init_params.rawdataOpts.audioRawDataMemoryMode = ZoomSDKRawDataMemoryModeHeap;
SDKError err = InitSDK(init_params);
if (err != SDKERR_SUCCESS) {
std::cerr << "InitSDK failed: " << err << std::endl;
return 1;
}
// Authenticate SDK with JWT
AuthContext auth_ctx;
auth_ctx.jwt_token = jwt_token_from_step1;
IAuthService* auth_service;
CreateAuthService(&auth_service);
auth_service->SetEvent(new MyAuthDelegate());
auth_service->SDKAuth(auth_ctx);Step 3: Join Meeting
// In onAuthenticationReturn callback
class MyAuthDelegate : public IAuthServiceEvent {
void onAuthenticationReturn(AuthResult ret) override {
if (ret == AUTHRET_SUCCESS) {
JoinParam join_param;
join_param.userType = SDK_UT_WITHOUT_LOGIN;
auto& params = join_param.param.withoutloginuserJoin;
params.meetingNumber = 1234567890;
params.userName = "Transcription Bot";
params.psw = meeting_password;
params.isVideoOff = true; // Bot doesn't need video
params.isAudioOff = false; // Need audio for transcription
params.app_privilege_token = obf_token; // From Step 1
meeting_service->Join(join_param);
}
}
};Step 4: Start Raw Recording & Subscribe to Audio
class MyMeetingDelegate : public IMeetingServiceEvent {
void onMeetingStatusChanged(MeetingStatus status, int iResult) override {
if (status == MEETING_STATUS_INMEETING) {
std::cout << "[BOT] Joined meeting successfully" << std::endl;
// Get recording controller
auto* record_ctrl = meeting_service->GetMeetingRecordingController();
// Check permission
SDKError can_record = record_ctrl->CanStartRawRecording();
if (can_record != SDKERR_SUCCESS) {
std::cerr << "[ERROR] Cannot start raw recording: " << can_record << std::endl;
std::cerr << "Need: host/co-host OR recording token" << std::endl;
return;
}
// Start raw recording (enables raw data access)
SDKError err = record_ctrl->StartRawRecording();
if (err != SDKERR_SUCCESS) {
std::cerr << "[ERROR] StartRawRecording failed: " << err << std::endl;
return;
}
std::cout << "[BOT] Raw recording started, subscribing to audio..." << std::endl;
// Subscribe to audio
auto* audio_helper = GetAudioRawdataHelper();
if (!audio_helper) {
std::cerr << "[ERROR] Failed to get audio helper" << std::endl;
return;
}
SDKError audio_err = audio_helper->subscribe(new TranscriptionAudioDelegate());
if (audio_err != SDKERR_SUCCESS) {
std::cerr << "[ERROR] Audio subscribe failed: " << audio_err << std::endl;
} else {
std::cout << "[BOT] Subscribed to audio successfully" << std::endl;
}
}
}
};Step 5: Process Audio & Send to Transcription Service
class TranscriptionAudioDelegate : public IZoomSDKAudioRawDataDelegate {
private:
AssemblyAIClient transcription_client;
std::ofstream debug_file; // For debugging: save raw audio
public:
TranscriptionAudioDelegate() {
// Initialize transcription service connection
transcription_client.connect();
// Optional: Save raw audio for debugging
debug_file.open("meeting_audio.pcm", std::ios::binary);
}
void onMixedAudioRawDataReceived(AudioRawData* data) override {
// Get audio properties
uint32_t sample_rate = data->GetSampleRate(); // Typically 32000 Hz
uint32_t channels = data->GetChannelNum(); // 1 (mono) or 2 (stereo)
uint32_t buffer_len = data->GetBufferLen();
char* buffer = data->GetBuffer();
// Send to transcription service
transcription_client.send_audio(buffer, buffer_len, sample_rate, channels);
// Optional: Save for debugging
if (debug_file.is_open()) {
debug_file.write(buffer, buffer_len);
}
}
void onOneWayAudioRawDataReceived(AudioRawData* data, uint32_t node_id) override {
// Per-user audio (optional - for speaker diarization)
// node_id identifies the speaker
}
~TranscriptionAudioDelegate() {
transcription_client.disconnect();
if (debug_file.is_open()) {
debug_file.close();
}
}
};Step 6: Handle Transcription Results
class AssemblyAIClient {
private:
WebSocketClient ws;
std::string api_key;
public:
void connect() {
ws.connect("wss://api.assemblyai.com/v2/realtime/ws?sample_rate=32000", {
{"Authorization": api_key}
});
// Listen for transcription results
ws.on_message([](const std::string& message) {
json result = json::parse(message);
if (result["message_type"] == "FinalTranscript") {
std::string text = result["text"];
float confidence = result["confidence"];
std::cout << "[TRANSCRIPT] " << text << " (confidence: " << confidence << ")" << std::endl;
// Store in database
save_to_database(text, timestamp);
}
});
}
void send_audio(char* buffer, size_t len, uint32_t sample_rate, uint32_t channels) {
// Convert PCM to base64 (AssemblyAI expects base64-encoded audio)
std::string encoded = base64_encode((unsigned char*)buffer, len);
json audio_data = {
{"audio_data", encoded}
};
ws.send(audio_data.dump());
}
};Production Patterns
Retry Logic for Meeting Join
See: meeting-sdk-bot.md
bool joinMeetingWithRetry(int max_attempts = 5, int retry_interval_ms = 60000) {
for (int attempt = 1; attempt <= max_attempts; attempt++) {
std::cout << "[JOIN] Attempt " << attempt << "/" << max_attempts << std::endl;
SDKError err = meeting_service->Join(join_param);
if (err == SDKERR_SUCCESS && waitForJoinCallback()) {
std::cout << "[JOIN] Success!" << std::endl;
return true;
}
if (attempt < max_attempts) {
std::cout << "[JOIN] Retrying in " << (retry_interval_ms / 1000) << "s..." << std::endl;
std::this_thread::sleep_for(std::chrono::milliseconds(retry_interval_ms));
}
}
std::cerr << "[JOIN] Failed after " << max_attempts << " attempts" << std::endl;
return false;
}Docker Deployment
Dockerfile:
FROM ubuntu:22.04
# Install dependencies
RUN apt-get update && apt-get install -y \
build-essential cmake \
libx11-xcb1 libxcb-xfixes0 libxcb-shape0 libxcb-shm0 \
libxcb-randr0 libxcb-image0 libxcb-keysyms1 libxcb-xtest0 \
libglib2.0-dev libcurl4-openssl-dev \
pulseaudio pulseaudio-utils
# Setup PulseAudio for headless audio
RUN mkdir -p ~/.config && \
echo "[General]\nsystem.audio.type=default" > ~/.config/zoomus.conf
# Copy SDK and app
COPY zoom_meeting_sdk/ /app/lib/
COPY transcription_bot /app/
# Setup PulseAudio virtual devices
COPY setup-pulseaudio.sh /app/
RUN chmod +x /app/setup-pulseaudio.sh
CMD ["/app/setup-pulseaudio.sh && /app/transcription_bot"]setup-pulseaudio.sh:
#!/bin/bash
# Start PulseAudio daemon
pulseaudio --start --exit-idle-time=-1
# Create virtual speaker
pactl load-module module-null-sink sink_name=virtual_speaker
# Create virtual microphone
pactl load-module module-null-sink sink_name=virtual_mic
echo "PulseAudio configured for headless operation"Configuration Management
Environment Variables (.env):
# Zoom SDK Credentials
ZOOM_CLIENT_ID=your_client_id
ZOOM_CLIENT_SECRET=your_client_secret
# Meeting Info
ZOOM_MEETING_NUMBER=1234567890
ZOOM_MEETING_PASSWORD=abc123
# Transcription Service
ASSEMBLYAI_API_KEY=your_api_key
# Bot Config
BOT_NAME="Transcription Bot"
BOT_JOIN_RETRY_ATTEMPTS=5
BOT_JOIN_RETRY_INTERVAL_MS=60000Loading config:
#include <cstdlib>
struct BotConfig {
std::string client_id;
std::string client_secret;
uint64_t meeting_number;
std::string meeting_password;
std::string bot_name;
int join_retry_attempts;
int join_retry_interval_ms;
};
BotConfig loadConfig() {
BotConfig cfg;
cfg.client_id = getenv("ZOOM_CLIENT_ID") ?: "";
cfg.client_secret = getenv("ZOOM_CLIENT_SECRET") ?: "";
cfg.meeting_number = std::stoull(getenv("ZOOM_MEETING_NUMBER") ?: "0");
cfg.meeting_password = getenv("ZOOM_MEETING_PASSWORD") ?: "";
cfg.bot_name = getenv("BOT_NAME") ?: "Transcription Bot";
cfg.join_retry_attempts = atoi(getenv("BOT_JOIN_RETRY_ATTEMPTS") ?: "5");
cfg.join_retry_interval_ms = atoi(getenv("BOT_JOIN_RETRY_INTERVAL_MS") ?: "60000");
return cfg;
}Common Issues & Solutions
Issue: Raw Recording Permission Denied
Error: CanStartRawRecording() returns SDKERR_NO_PERMISSION
Solution:
Bot needs to be host/co-host, OR
Use recording token from REST API, OR
Host grants recording permission manually
See: meeting-sdk-bot.md#raw-recording-permission-denied
Issue: No Audio in Docker
Error: Audio subscription succeeds but no audio callbacks
Solution: Create ~/.config/zoomus.conf:
mkdir -p ~/.config
echo "[General]\nsystem.audio.type=default" > ~/.config/zoomus.confSee: linux-reference.md#pulseaudio-setup
Issue: Callbacks Not Firing
Error: onMeetingStatusChanged() never called after Join()
Solution: Add GLib main loop:
#include <glib.h>
GMainLoop* loop = g_main_loop_new(NULL, FALSE);
g_main_loop_run(loop); // Blocks until quitRelated Use Cases
AI Meeting Assistant - Add AI analysis on top of transcription
Recording Bot - Record video + audio with sync
Real-time Media Streams - Alternative: RTMS for invisible bots
Related Skills
meeting-sdk/linux - Complete Meeting SDK Linux guide
zoom-rest-api - Get meetings, OBF tokens
zoom-oauth - JWT token generation
Sample Code
Complete sample: meeting-sdk/linux/concepts/high-level-scenarios.md
Official samples:
Key Takeaways
✅ Use OBF tokens for joining external meetings (require owner present)
✅ Setup PulseAudio for Docker/headless audio access
✅ Call StartRawRecording() before subscribing to audio
✅ Use heap memory mode for raw data (ZoomSDKRawDataMemoryModeHeap)
✅ Implement retry logic for meeting join (OBF requires owner present)
✅ Add GLib main loop for callbacks to work
✅ Stream audio in real-time for best transcription latency
Requirements and compatibility
Written for: Claude Code, Claude apps
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: Claude Code frontmatter, Needs an MCP server
Security
What our scanner noticed· Medium risk
- Possible data-exfiltration endpoints
- Instructions that use the network
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
- Anthropic (Official)
- Distributed by
- Anthropic
- Source
- anthropics/knowledge-work-plugins · partner-built/zoom-plugin/skills/general · commit e050c2e
- Licence
- MIT License (redistribution allowed)
- LICENSE (added by AutoGineer from partner-built/zoom-plugin/LICENSE)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Zoom or Anthropic.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download zoom-general.zip