YouTube transcription integration

For channels that need a transcript of every upload for descriptions, chapters and repurposing. The job: turn each new upload into a timestamped transcript the moment it publishes.

The one thing that breaks this

YouTube's own auto-captions are unpunctuated and have no speaker labels, which is why they read badly when pasted into a description or a course outline.

ModuleWhipscribe YouTube connector

ShapeConnector

Recipes1

Wiring it up

1 · Trigger

Any of these start the run:

New video on channel
RSS of the channel feed

2 · Submit from Whipscribe YouTube connector

# submit — returns immediately, does not block
curl -X POST https://whipscribe.com/api/v1/transcribe/url \
  -H "X-API-Key: $KEY" \
  -H "Idempotency-Key: youtube-$FILE_ID" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com/recording.mp4",
       "diarize":true,
       "word_timestamps":true}'

→ 202 {"job_id":"a1b2…","status":"queued"}

# then poll — a self-serve (Pro) key collects by polling
curl "https://whipscribe.com/api/v1/jobs/$JOB" -H "X-API-Key: $KEY"
→ {"status":"processing"} … {"status":"done"}

Retry safety. Only pull videos you own or have rights to. The connector is scoped to your own channel for that reason.

3 · Collect

Connect the account once; we fetch the file ourselves.

# one job, every format — never re-submit per format
curl "https://whipscribe.com/api/v1/jobs/$JOB/result?format=txt" -H "X-API-Key: $KEY"
curl "https://whipscribe.com/api/v1/jobs/$JOB/result?format=srt" -H "X-API-Key: $KEY"
curl "https://whipscribe.com/api/v1/jobs/$JOB/result?format=vtt" -H "X-API-Key: $KEY"

What your key can actually do

Tier	Req/min	Minutes/day	Longest file	Results	How you get it
Free	10	60 min	2 hours	Poll	Not self-serve — existing keys only
Pro	60	Unlimited	10 hours	Poll	What POST /v1/keys mints, once your account has credit
Enterprise	120	Unlimited	10 hours	Signed webhooks	Talk to us

Collecting results. Self-serve keys are Pro tier, and Pro collects results by polling — webhook_url on a Pro key returns 403 TIER_FORBIDDEN. Signed callbacks are an Enterprise feature.

What it costs to run

Rate$0.008 / min

Per audio hour$0.48

10 hours of audio$4.80

CreditsNever expire

$8 per 1,000 minutes — about $0.48 an audio hour — and credits never expire.

Why run it here

No subscription to size wrongCompeting transcription tools sell $25–$65 monthly plans with a minute cap that resets whether you used it or not. Credits here are bought once and do not expire, so a quiet month costs nothing and a backlog run does not need an upgrade.

Your audio is not sent to a third-party modelTranscription runs on our own GPUs in our own private cloud. Nothing is forwarded to OpenAI or any other vendor's API, which is usually the blocking question when the recordings are customer calls or unreleased material.

One job, every formattxt, json, srt, vtt and docx all come from the same job id. Re-submitting a file per format is the most common way teams pay several times for one transcription.

Built to be retriedIdempotency-Key means an automation platform's automatic retry returns the original job instead of billing a second one. Every no-code platform retries; most transcription APIs charge you for it.

Recipes that use YouTube

Caption lecture recordings for accessibilityCaptions are required, manual captioning is slow, and auto-captions from video platforms have no punctuat…12-week course ≈ $12

Try the quality free, then wire it up

Your first transcript in the web app is free, any length, no card — that is how to check accuracy on your own audio before writing any code. The API itself has no free tier: a key is self-serve once your account has credit ($50 minimum, spendable on transcription, and it does not expire). $8 per 1,000 minutes — about $0.48 an audio hour — and credits never expire.

Transcribe a file free →Create an API key API reference