scribe

anthropics/knowledge-work-plugins

Zoom AI Services Scribe reference for transcribing uploaded or stored media via fast mode, batch jobs, and webhook pipelines.

Source View on skills.sh

What is scribe?

Reference skill for integrating Zoom AI Services Scribe to transcribe audio and video files. Use this when handling uploaded or stored media that needs conversion to text, including fast-mode single-file transcription, asynchronous batch jobs, Build-platform JWT authentication, and transcript pipeline design.

Synchronous fast-mode transcription for single files up to 100 MB and 2 hours
Asynchronous batch job submission and status polling for large media archives
Webhook-driven pipeline notifications for batch job completion and per-file results
Build-platform JWT generation and credential handling for API authentication
Browser microphone pseudo-streaming via repeated short file uploads with transcript stitching

How to install scribe

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill scribe

Prerequisites

Zoom Build-platform credentials (account and app)
HS256 JWT generation capability
Familiarity with REST API authentication and async job patterns

Claude Code

Cursor

Windsurf

Cline

How to use scribe

1.Obtain Build-platform credentials and generate an HS256 JWT token
2.Choose fast mode for single files under 100 MB or batch mode for archives and large sets
3.Submit transcription request to POST /aiservices/scribe/transcribe (fast) or POST /aiservices/scribe/jobs (batch)
4.For batch jobs, poll GET /aiservices/scribe/jobs/{jobId} or configure webhook notifications for status updates
5.Retrieve and post-process transcript JSON from response or webhook payload

Use cases

Good for

On-demand transcription of user-uploaded meeting recordings or clips
Batch transcription of stored S3 call archives or compliance archives
Webhook-driven ETL pipeline that writes transcripts to database or search index
Re-transcription of Zoom-managed recordings after exporting to your own storage
Offline compliance or QA workflows requiring timestamps, channel separation, and speaker hints

Who it's for

Backend developers building transcription workflows
Compliance and QA teams processing recorded media
Platform engineers designing webhook-driven ETL pipelines
Developers integrating Zoom recordings into custom applications

scribe FAQ

What is the difference between fast mode and batch mode?

Fast mode (POST /aiservices/scribe/transcribe) is synchronous and handles single files up to 100 MB and 2 hours; batch mode (POST /aiservices/scribe/jobs) is asynchronous and suited for multiple files or archives. Fast mode can timeout in browser contexts despite backend success; batch mode is preferred for larger or unpredictable media.

Can I transcribe live Zoom meetings in real-time?

No. Scribe is for uploaded or stored media files. For live meeting transcription, use the RTMS (Real-Time Media Service) skill instead.

How do I handle browser timeouts with fast-mode transcription?

Wrap fast-mode requests in an async request/polling wrapper instead of holding the browser open. Treat frontend 504 errors with backend 200 responses as browser/edge timeouts, not transcription failures. For larger files, use batch mode.

What is the browser microphone pseudo-streaming pattern?

Capture microphone audio in 5-10 second chunks, upload each via async fast-mode, poll for completion, and append transcripts in sequence. This is a fallback demo pattern with overhead and stitching complexity; prefer RTMS for true live streaming.

How do I verify webhook signatures from batch job notifications?

Use HMAC verification patterns; optionally chain the webhooks skill for generic HMAC receiver hardening and signature validation.

Full instructions (SKILL.md)

Source of truth, from anthropics/knowledge-work-plugins.

name: scribe description: "Reference skill for Zoom AI Services Scribe. Use after routing to a transcription workflow when handling uploaded or stored media, Build-platform JWT auth, fast mode transcription, batch jobs, or transcript pipeline design." user-invocable: false triggers:

"scribe"
"ai services scribe"
"zoom scribe"
"transcribe audio file"
"transcribe video file"
"batch transcription"
"fast mode transcription"
"build platform jwt"

Zoom AI Services Scribe

Background reference for Zoom AI Services Scribe across:

synchronous single-file transcription (POST /aiservices/scribe/transcribe)
asynchronous batch jobs (/aiservices/scribe/jobs*)
browser microphone pseudo-streaming via repeated short file uploads
webhook-driven batch status updates
Build-platform JWT generation and credential handling

Official docs:

Routing Guardrail

If the user needs uploaded or stored media transcribed into text, route here first.
If the user needs live meeting media without file-based upload/batch jobs, route to ../rtms/SKILL.md.
If the user needs Zoom REST API inventory for AI Services paths, chain ../rest-api/SKILL.md.
If the user needs webhook signature patterns or generic HMAC receiver hardening, optionally chain ../webhooks/SKILL.md.

Quick Links

Core Workflow

Get Build-platform credentials and generate an HS256 JWT.
Choose fast mode for one short file or batch mode for stored archives / large sets.
Submit the transcription request.
For batch jobs, poll job/file status or receive webhook notifications.
Persist and post-process transcript JSON.

Hosted Fast-Mode Guardrail

The formal fast-mode API limits are 100 MB and 2 hours, but hosted browser flows can still time out before the upstream response returns.
Current deployed-sample observations:
- ~17.2 MB MP4 completed in about 26s
- ~38.6 MB MP4 completed in about 26-37s
- ~59.2 MB MP4 completed in about 32-34s on the backend
- some ~59.2 MB browser requests still surfaced as frontend 504 while backend logs later showed 200
Treat frontend 504 plus backend 200 as a browser/edge timeout race, not an automatic transcription failure.
For hosted UIs, prefer an async request/polling wrapper for fast mode instead of holding the browser open for the full upstream response.
For larger or less predictable media, prefer batch mode even when the file is still within the formal fast-mode size limit.

Browser Microphone Pattern

scribe does not expose a documented real-time streaming API surface.
If you want a browser microphone experience, use pseudo-streaming:
1. capture microphone audio in short chunks
2. upload each chunk through the async fast-mode wrapper
3. poll for completion
4. append chunk transcripts in sequence
Recommended starting cadence:
- chunk size: 5 seconds
- acceptable range: 5-10 seconds
- in-flight chunk requests: 2-3
This is a practical UI pattern for incremental transcript updates, not a substitute for rtms.
Treat this as a fallback demo pattern, not the preferred production architecture.
It adds repeated upload overhead, chunk-boundary drift, browser codec/container variability, and transcript stitching complexity.
If the user asks for actual live stream ingestion, low-latency continuous media, or server-push media transport, route to ../rtms/SKILL.md instead.

Endpoint Surface

Mode	Method	Path	Use
Fast	`POST`	`/aiservices/scribe/transcribe`	Synchronous transcription for one file
Batch	`POST`	`/aiservices/scribe/jobs`	Submit asynchronous batch job
Batch	`GET`	`/aiservices/scribe/jobs`	List jobs
Batch	`GET`	`/aiservices/scribe/jobs/{jobId}`	Inspect job summary/state
Batch	`DELETE`	`/aiservices/scribe/jobs/{jobId}`	Cancel queued/processing job
Batch	`GET`	`/aiservices/scribe/jobs/{jobId}/files`	Inspect per-file results

High-Level Scenarios

On-demand clip transcription after a user uploads one recording.
Batch transcription of stored S3 call archives.
Webhook-driven ETL pipeline that writes transcripts to your database/search index.
Re-transcription of Zoom-managed recordings after exporting them to your own storage.
Offline compliance or QA workflows that need timestamps, channel separation, and speaker hints.