A video in.
A factual, timestamped description out.
Shots and how they begin. Camera support and moves. Colour and light. People, activities and moments. Speech with speakers. On-screen text. Music with tempo and key. Where and when it was recorded. Measured where a number can be measured, observed where a model looked, never an opinion about what to do with the footage.
$5 of credit on sign-up. No card until you need more.
Three calls
1. Upload
POST /v1/uploads gives you a URL. PUT the file there. Up to 300 MB and an hour of footage.
2. Analyse
POST /v1/analyses with the upload and a detail level. You get a job id back at once; the estimate is held against your balance.
3. Read
Poll the job or give a webhook URL. GET the result as the smartmedia document, the full analysis JSON, or readable text.
curl -X POST $API/v1/uploads -H "Authorization: Bearer sm_live_…" \
-d '{"filename":"clip.mp4","bytes":12345678}'
curl -X PUT "$UPLOAD_URL" -H "Content-Type: video/mp4" --data-binary @clip.mp4
curl -X POST $API/v1/analyses -H "Authorization: Bearer sm_live_…" \
-d '{"upload_id":"up_…","detail":"standard"}'
curl "$API/v1/analyses/an_…/result?format=json" -H "Authorization: Bearer sm_live_…"Priced per minute of video
Prepaid credit, never expires. A failed job is never charged. The same file at the same level is free the second time.
facts
1¢ / minFile facts, cuts and punch-ins, camera support and moves, colour and light, loudness, silences, music tempo and key.
transcript
3¢ / minEverything in facts, plus words, sentences, paragraphs and speakers from Deepgram.
standard
20¢ / minOne model pass over the video: shot forms, activities, people, on-screen text, who is speaking, scenes, venue.
detailed
35¢ / minThe exhaustive pass: fine-grained actions with their details, for edits that need every beat.
Consolidation across levels adds 5¢ per minute. Minimum charge per job from 1¢ to 30¢ by level. Every price is on GET /v1/estimate before you run anything.