scribe

Name: scribe
Author: anthropics

Design and run media transcription workflows with auth, batching, and pipelines.

Stars

★ 22,528

Source

GitHub

Updated

2026-07-11

// securityLow risk

Prompt only, no code
Open source
Community-trusted· 22.5k

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "scribe" skill from askskill:
1. Download https://raw.githubusercontent.com/anthropics/knowledge-work-plugins/main/partner-built/zoom-plugin/skills/scribe/SKILL.md
2. Save it as ~/.claude/skills/scribe/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Design a transcription workflow

Prompt

I'm building an app that automatically transcribes uploaded audio and video. Design a complete workflow for Zoom AI Services Scribe, including post-upload routing, Build-platform JWT authentication, fast mode use cases, retry handling, and result delivery.

Expected

An end-to-end transcription workflow plan with key steps, authentication, error handling, and delivery paths.

Create a batch transcription plan

Prompt

Help me design a batch transcription solution for a large library of stored media using Zoom AI Services Scribe. Explain job partitioning, queue strategy, concurrency control, status tracking, and cost-versus-speed tradeoffs.

Expected

An actionable batch-processing architecture showing how to complete large-scale transcription efficiently and reliably.

Plan a transcript pipeline

Prompt

I need to feed transcription results into subtitle, summarization, and search systems. Based on Zoom AI Services Scribe, design a transcript pipeline covering result storage, timestamp handling, format conversion, and downstream service interface recommendations.

Expected

A transcript-processing pipeline design ready for subtitle generation, summarization, and full-text search integration.

// docs

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.

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.