Transcribe and probe in one call: video-inspect STT at $0.01/min

Set transcribe: true on POST /v1/video-inspect and the response adds a transcript with text, words[], optional sentence segments[] and an audio_url. The transcript is priced at $0.01 per audio minute on top of the inspect's Modal compute (Video inspect).

Request

Pass duration_seconds so the hold matches the clip; without it Sume reserves one minute, and the hint is capped at 600 s.

curl -X POST https://api.sume.com/v1/video-inspect \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: inspect-stt-001" \
  -d '{
    "video_url": "https://media.sume.com/artifacts/artf_demo/talk.mp4",
    "frames": false,
    "transcribe": true,
    "language_code": "en",
    "duration_seconds": 240,
    "segmentation": {"mode": "sentence"}
  }'

Transcript cost by clip length

Only the STT part, from the published per-minute rate; the Modal compute for the probe is billed on top.

Refusals

• video_inspect_transcribe_required when language_code, segmentation or duration_seconds is sent without transcribe: true.
• inspect_source_has_no_audio for a silent clip: probe with frames: false and read probe.has_audio first.
• Sentence segmentation accepts silence_split_seconds from 0.2 to 3.

Source and result

The video_url must be a media.sume.com artifact or asset in your workspace; the API does not fetch from the open internet, so import the clip first with POST /v1/media-imports. The default mode is sync: the handler waits up to 30 seconds and returns 200 with the result, or 202 with a queued job that you read later at GET /v1/video-inspect/{id}. The duration hint tops out at 600 s.