Caption lecture recordings for accessibility

Education teams with an accessibility obligation and a recording backlog. Captions are required, manual captioning is slow, and auto-captions from video platforms have no punctuation or speaker labels.

The flow

1. TriggerThe lecture recording is published or lands in storage.
2. SubmitOne job produces every format — you do not run it again per format.
3. CollectPull result?format=srt and result?format=vtt from the same job id.
4. AttachUpload the caption track alongside the video.

# submit — returns immediately, does not block
curl -X POST https://whipscribe.com/api/v1/transcribe/url \
  -H "X-API-Key: $KEY" \
  -H "Idempotency-Key: lecture-recordings-to-captioned-lessons-$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 12-week course of two-hour lectures is 24 hours — about $12 for the term. $24 per 5,000 minutes — about $0.29 an audio hour — and credits never expire.

Why this needs an API rather than a person

Compliance is per-item and continuous, which is exactly the shape a human should not be in.

Build it on