The Vision API supports two approaches for generating metadata tags for your videos: quick tagging and indexed tagging.
By default, both approaches can return the following fields:
Description: stringViolence: booleanProfanity: booleanAdultContent: booleanDrugs: booleanAlcohol: booleanGambling: booleanPolitical: booleanExpectedCTR: number (0–100)ViralityScore: number (0–100)Keyword: array of stringsMoodTone: array of stringsYou can add, remove, and customize output fields. Contact us to optimize outputs for your use case.
Quick tagging is suitable for short videos (e.g., under 30 seconds). Videos are processed ad-hoc and videos are not stored.
POST /v1/qa/quicktagvideo_id (optional): ID of the video to analyzevideo_url (optional): URL of the video to analyze (either video_id or video_url is required)Indexed tagging allows you to generate tags for previously uploaded and indexed videos. Indexed tagging is more suitable for longer videos.
Before using Indexed Tagging, ensure your video has been successfully indexed:
index=true using the /videos/upload endpoint."indexed""indexing"POST /v1/qa/indexedtagvideo_id (required): ID of the previously indexed videoDiscounted pricing is available for large-volume batch processing: