scribe
This skill enables building and debugging Zoom AI Services Scribe transcription pipelines for live interactive audio streams, uploaded files, or stored media…
Identity proven by GitHub's verified organisation badge (zoom)
- Agents
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
- License
- MIT (permissive)
- Pin
- 1093682pinned Oct 9, 2026
- Context cost
- about 510 tokenswhen the skill loads
- GitHub stars
- 2on zoom/zoom-plugin-codex
- Scripts
- None found
What it does
“Use when building or debugging Zoom AI Services Scribe transcription in Live, Fast, or Batch mode, including secure WebSocket PCM16 streams, individual files, and stored-media jobs.”
Generated summary from the skill's own text
This skill enables building and debugging Zoom AI Services Scribe transcription pipelines for live interactive audio streams, uploaded files, or stored media in Live, Fast, or Batch modes. It handles secure WebSocket PCM16 streaming, credential setup, JWT management, and integrates with downstream summarization or translation workflows. Use it to set up end-to-end transcription with proper error handling, webhook callbacks, and operational monitoring.
When to use it
- Building live transcription from app-owned microphone or voice-agent streams
- Processing pre-recorded files or Zoom stored media for transcription
- Setting up async batch transcription with webhook callbacks and retries
- Debugging transcription pipeline issues like auth, audio format, or session lifecycle
When not to
- Transcribing Zoom meetings or Video SDK sessions - use RTMS or Meeting SDK bot instead
- Tasks requiring only summarization or translation without transcription first
Install
These commands install from the publisher's repository and need no account.
skills CLI
npx skills add zoom/zoom-plugin-codex --skill scribeInstalls from the repository's default branch, which may have changed since the commit we checked.
GitHub CLI 2.90 or later
gh skill install zoom/zoom-plugin-codex scribe@10936829584d5b232e8edd9e6a6cab48729d2c52Installs the commit we checked (1093682).
Copy by hand
Download the folder at 1093682 and put it in .claude/skills/scribe for Claude Code and in .agents/skills/scribe for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Claude Code plugin
/plugin install zoom-plugin@claude-plugins-officialThe publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.
Copy for your agent
A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.
Prompt
Install the agent skill "scribe" by Zoom. Source, pinned to commit 10936829584d5b232e8edd9e6a6cab48729d2c52: https://github.com/zoom/zoom-plugin-codex/tree/10936829584d5b232e8edd9e6a6cab48729d2c52/skills/scribe 1. Download that folder at exactly this commit. Do not use the default branch. 2. Copy every file unchanged, keeping the folder structure, into .claude/skills/scribe/ for Claude Code and .agents/skills/scribe/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist. 3. Do not edit the files, and do not run any script in the folder unless I ask you to. 4. When you are done, list the files you copied and where you put them. Listing and checks: https://www.agentnative.dev/skills/zoom/scribe-zoom-plugin-codex
SKILL.md at the pin
--- name: scribe description: Use when building or debugging Zoom AI Services Scribe transcription in Live, Fast, or Batch mode, including secure WebSocket PCM16 streams, individual files, and stored-media jobs. --- # Zoom AI Services Scribe Use this skill for Zoom Scribe transcription pipelines over live interactive audio, uploaded files, or stored media. Use Scribe Live Mode for app-owned microphone or voice-agent streams. If the source is a Zoom meeting, webinar, or Video SDK session, compare against RTMS or a Meeting SDK bot first. Chain Summarizer or Translator for downstream processing. ## Workflow 1. Confirm the media source, language, expected latency, and whether Live, Fast, or Batch mode fits. 2. Set up Build-platform credentials and JWT handling separately from application transcription logic. 3. For Live Mode, keep the JWT on a trusted backend, configure the WebSocket session, and stream binary PCM16 frames through a backend connection or browser relay. 4. For Fast or Batch mode, design file ingestion, retries, webhook callbacks, and persistence before connecting downstream AI workflows. 5. Implement the smallest working transcription flow and response/event parser, then add operational monitoring. 6. Debug by checking credential audience, mode, audio format, session lifecycle, file size, backend timeout, and webhook delivery. ## References - Full preserved guide: [references/full-guide.md](references/full-guide.md) - Auth and processing modes: [concepts/auth-and-processing-modes.md](concepts/auth-and-processing-modes.md) - High-level scenarios: [scenarios/high-level-scenarios.md](scenarios/high-level-scenarios.md) - Live Mode WebSocket example: [examples/live-mode-websocket.md](examples/live-mode-websocket.md) - Fast mode Node example: [examples/fast-mode-node.md](examples/fast-mode-node.md) - Batch webhook pipeline: [examples/batch-webhook-pipeline.md](examples/batch-webhook-pipeline.md) - API reference: [references/api-reference.md](references/api-reference.md) - Common drift and breaks: [troubleshooting/common-drift-and-breaks.md](troubleshooting/common-drift-and-breaks.md) - Chain summaries: [../summarizer/SKILL.md](../summarizer/SKILL.md) - Chain translations: [../translator/SKILL.md](../translator/SKILL.md)
From zoom/zoom-plugin-codex at 1093682, shown as plain text under its license: MIT (permissive). The license text is in LICENSE.
View SKILL.md on GitHub at 1093682Files
- SKILL.md2.3 KB · 6382095b65f1
- RUNBOOK.md5.1 KB · 0cbe32cbc4d4
- concepts/
- auth-and-processing-modes.md3.8 KB · 8e7c12dc503c
- examples/
- batch-webhook-pipeline.md1.6 KB · d765270cbc35
- fast-mode-node.md1.8 KB · d5f4a1eff43a
- live-mode-websocket.md2.3 KB · 5f991ab0762c
- references/
- api-reference.md4.3 KB · e702461ed156
- environment-variables.md2.0 KB · 0e0a70fb55e6
- full-guide.md6.6 KB · 3da50c6e906e
- samples-validation.md3.5 KB · 623b7dc6a6fa
- versioning-and-drift.md2.8 KB · 958e44053616
- scenarios/
- high-level-scenarios.md3.4 KB · cb508a3f13f9
- troubleshooting/
- common-drift-and-breaks.md5.5 KB · 1a69ca05d733
13 files, 45 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.
Skill folder on GitHub at 1093682More from Zoom
build-zoom-bot
This skill guides building Zoom bots that join meetings, capture media, or process live transcripts using Meeting SDK and RTMS.
Claude Code, Codex, Cursor +4 · about 300 tokens · pinned 6 days ago
build-zoom-contact-center-app
This skill provides implementation guidance for Zoom Contact Center integrations across desktop apps, web embeds, and native mobile platforms.
Claude Code, Codex, Cursor +3 · about 1.2K tokens · pinned 6 days ago
build-zoom-meeting-app
This skill guides agents in building embedded Zoom meeting applications by helping select appropriate SDKs, plan authentication flows, and route to Meeting…
Claude Code, Codex, Cursor +4 · about 310 tokens · pinned 6 days ago
build-zoom-meeting-sdk-app
This skill provides reference guidance for implementing Zoom Meeting SDK across web, mobile, desktop, and Linux platforms.
Claude Code, Codex, Cursor +3 · about 2.7K tokens · pinned 6 days ago
build-zoom-phone-integration
This skill provides reference guidance for implementing Zoom Phone integrations using OAuth, REST APIs, webhooks, Smart Embed iframe components, URI schemes…
Claude Code, Codex, Cursor +3 · about 1.1K tokens · pinned 6 days ago
build-zoom-rest-api-app
This skill provides comprehensive reference documentation and examples for building server-side integrations with the Zoom REST API, covering 600+ endpoints…
Claude Code, Codex, Cursor +3 · about 6.7K tokens · pinned 6 days ago
Related in Backend and APIs
nvflare-orient
Routes NVFLARE requests to appropriate downstream skills based on user intent and preliminary source inspection findings.
by NVIDIAOfficial publisher
Claude Code, Codex, Cursor +4 · about 600 tokens · pinned 6 days ago
cloudflare-email-service
This skill enables agents to send transactional emails and route incoming emails using Cloudflare's Email Service platform.
by CloudflareOfficial publisher
Claude Code, Codex, Cursor +4 · about 1.6K tokens · pinned 6 days ago
durable-objects
Build and debug Cloudflare Durable Objects applications for stateful coordination and persistent storage on the edge.
by CloudflareOfficial publisher
Claude Code, Codex, Cursor +4 · about 1.5K tokens · pinned 6 days ago
workers-best-practices
This skill guides code review and development of Cloudflare Workers by applying best practices for production readiness.
by CloudflareOfficial publisher
Claude Code, Codex, Cursor +4 · about 1.3K tokens · pinned 6 days ago
supabase
This skill enables the agent to work with Supabase products including Database, Auth, Edge Functions, Realtime, Storage, and Vectors.
by SupabaseOfficial publisher
Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 6 days ago
apple
This skill emulates Apple's OAuth and OIDC services for local development and testing.
by VercelOfficial publisher
Claude Code, Codex, Cursor +4 · about 1.9K tokens · pinned 6 days ago