Write SOPs from how-we-do-it recordings

Operations teams who document by recording rather than writing. Process knowledge lives in someone's screen recording and leaves when they do.

The flow

1. TriggerA new recording is shared in the workspace.
2. SubmitSubmit the download URL; screen recordings are narration-heavy and transcribe cleanly.
3. StructureNarration is already sequential — the steps are usually in order in the transcript.
4. PublishWrite the procedure into the wiki with a link back to the recording.

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

What it costs

A 40-recording documentation backlog at 20 minutes each is about 13 hours — roughly $6.40. $24 per 5,000 minutes — about $0.29 an audio hour — and credits never expire.

Why this needs an API rather than a person

The recordings already exist. Nothing new has to be produced for this to pay off.

Build it on