Metadata Tagging
The Vision API supports two approaches for generating metadata tags for your videos: quick tagging and indexed tagging.
Default Output Fields
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 strings
You can add, remove, and customize output fields. Contact us to optimize outputs for your use case.
Quick Tagging
Quick tagging is suitable for short videos (e.g., under 30 seconds). Videos are processed ad-hoc and videos are not stored.
Endpoint
POST /qa/quicktag
Request
Bash
Python
Parameters
video_id
(optional): ID of the video to analyzevideo_url
(optional): URL of the video to analyze (eithervideo_id
orvideo_url
is required)output_fields
(optional): Subset of fields to return; defaults to standard fields
Indexed Tagging
Indexed tagging allows you to generate tags for previously uploaded and indexed videos. Indexed tagging is more suitable for longer videos.
Bash
Python
Prerequisites
Before using Indexed Tagging, ensure your video has been successfully indexed:
- Upload a video with
index=true
using the/videos/upload
endpoint. - Check indexing status - it should be
"indexed"
- Wait for processing if status is
"indexing"
Endpoint
POST /qa/indexedtag
Request
Parameters
video_id
(required): ID of the previously indexed videooutput_fields
(optional): Subset of fields to return
Pricing
Discounted pricing is available for large-volume batch processing:
- Quick tagging input: $0.004 per input video minute
- Indexed tagging input: $0.03 per input video minute
- Outputs (both): $2 per 1M output tokens