Labsco
anthropics logo

scribe

✓ Official★ 22,378

by anthropic · part of anthropics/knowledge-work-plugins

Wiring Zoom's transcription service into your own software, so the recordings you already have come back as text you can search, store and act on.

🔥🔥✓ VerifiedFree
🧩 One of 177 skills in the anthropics/knowledge-work-plugins package — works on its own, and pairs well with its siblings.

WHEN YOUR AGENT SHOULD USE IT

A QUICK BOUNDARY

USE FOR

  • Transcribe one short recording and get the text straight back.
  • Send a whole archive of call recordings off to transcribe in the background.
  • Build a webhook-driven pipeline that writes transcripts straight to your database.
  • Debug a Build-platform JWT or credential problem blocking a transcription request.

DO NOT USE FOR

  • Live meeting audio or real-time streaming transcription — use the rtms skill instead.

This is the playbook your agent receives when the skill activates — you don't need to read it to use the skill, but it's here to audit before installing.

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.
  1. concepts/auth-and-processing-modes.md
  2. scenarios/high-level-scenarios.md
  3. examples/fast-mode-node.md
  4. examples/batch-webhook-pipeline.md
  5. references/api-reference.md
  6. references/environment-variables.md
  7. references/samples-validation.md
  8. references/versioning-and-drift.md
  9. troubleshooting/common-drift-and-breaks.md
  10. RUNBOOK.md

Core Workflow

  1. Get Build-platform credentials and generate an HS256 JWT.
  2. Choose fast mode for one short file or batch mode for stored archives / large sets.
  3. Submit the transcription request.
  4. For batch jobs, poll job/file status or receive webhook notifications.
  5. 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

ModeMethodPathUse
FastPOST/aiservices/scribe/transcribeSynchronous transcription for one file
BatchPOST/aiservices/scribe/jobsSubmit asynchronous batch job
BatchGET/aiservices/scribe/jobsList jobs
BatchGET/aiservices/scribe/jobs/{jobId}Inspect job summary/state
BatchDELETE/aiservices/scribe/jobs/{jobId}Cancel queued/processing job
BatchGET/aiservices/scribe/jobs/{jobId}/filesInspect 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.

Chaining

Operations

  • RUNBOOK.md - 5-minute preflight and debugging checklist.