Package title, description, and thumbnail

Generate metadata for a video already in the library, then read the results.

Call GET /characters and GET /brand-voices (videos:read) for ids. The same thumbnail object works on import (products.packaging.thumbnail) and on zeroPromptThumbnail here. Full Creative vs Precision instructions: Generate a thumbnail.

Faceless Creative:

curl -sS -X POST "$BRAIV_API_BASE/videos/$VIDEO_ID/packaging" \
  -H "Authorization: Bearer $BRAIV_API_KEY" -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d '{"generateTitle":{"enabled":true,"titleType":"informational"},"generateDescription":{"enabled":true,"descriptionType":"youtube-description"},"zeroPromptThumbnail":{"enabled":true}}'

Creative with a saved character:

"zeroPromptThumbnail": {
  "enabled": true,
  "pipelineMode": "thumbnail-v2",
  "characterCount": 1,
  "characters": [{"characterId": "char_01"}],
  "brandVoiceId": "bv_01"
}

Precision with opaque key-moment detect:

"zeroPromptThumbnail": {
  "enabled": true,
  "pipelineMode": "thumbnail-precision",
  "autoDetectContentReferences": true,
  "contentSlotCount": 2,
  "brandVoiceId": "bv_01"
}

Poll each packaging_{videoId}_{type} job, then GET /videos/{id}/packaging.