Skip to main content

​
Introduction

Detectors are the building blocks of judges. Each detector analyzes specific aspects of content and can be configured with custom parameters. When creating a judge, you specify which detectors to use and their configurations.

​
Configuration Format

When creating a judge using the v1 endpoint, detectors are configured in the detectors array: 
{
  "name": "My Judge",
  "description": "Judge description",
  "content_type": "video",
  "detectors": [
    {
      "detector_name": "video_specs",
      "config": {
        "min_width": 1920,
        "min_height": 1080,
        "min_fps": 24
      }
    },
    {
      "detector_name": "audio_noise",
      "config": {}
    }
  ]
}

​
Available Detectors

​
Content Quality Detectors

DetectorDescription
audio_noiseDetects background noise and audio quality issues
image_sharpnessDetects blurry or out-of-focus images
image_specsValidates image dimensions and aspect ratios
lightingAnalyzes lighting quality in visual content
video_qualityValidates video technical specifications
video_specsChecks video dimensions, duration, and frame rate

​
Content Matching Detectors

DetectorDescription
audio_matchingMatches audio against reference content
splitscreen_video_matchingMatches split-screen video content
video_matchingMatches video against reference content
video_matching_descriptionMatches video against text description

​
Content Analysis Detectors

DetectorDescription
content_qualityEvaluates overall content quality
languageDetects and validates content language
sentimentAnalyzes emotional tone and sentiment
transcript_policyChecks transcript against policy guidelines
transcript_productDetects product mentions in transcripts

​
Visual Analysis Detectors

DetectorDescription
backgroundAnalyzes background elements
framingEvaluates shot composition and framing
image_ip_infringementChecks for potential IP violations
overlaysDetects text overlays and graphics
product_applicationDetects product usage demonstrations
subtitlesDetects subtitle presence
wardrobeAnalyzes clothing and appearance

​
Audio Analysis Detectors

DetectorDescription
pronunciationChecks brand/product name pronunciation
voice_overDetects voice-over narration

​
Metadata Detectors

DetectorDescription
title_and_descriptionAnalyzes the content title and description for topic, mentions, and hashtags
transition_detectionDetects scene transitions and cuts

​
Reference Content

Some detectors require reference content (e.g., reference videos, audio files) for comparison. Reference content must be uploaded to Google Cloud Storage and provided as gs:// URIs.

​
Detectors Requiring Reference Content

  • audio_matching - Requires reference_audio
  • video_matching - Requires reference_video
  • splitscreen_video_matching - Requires at least one of source_video_reference or bottom_content_reference
  • pronunciation - Optional brand_audio_url and product_audio_url

​
Uploading Reference Content

  1. Use the /v1/judges/reference_content endpoint to get a pre-signed upload URL
  2. Upload your reference file to the provided URL
  3. Use the returned reference_content_uri in your detector configuration

​
Configuration Validation

  • Detector names must be valid (from the list above)
  • Required configuration keys must be provided for each detector
  • Reference content URIs must use the gs:// scheme
  • File extensions for reference content must match allowed types

​
Next Steps

  • See individual detector documentation for detailed configuration options
  • Check the Create Judge endpoint for full examples
  • Review detector-specific configuration schemas for required and optional parameters