Video

Audio-Visual SyncNet

Detects misalignment between lip movements and audio to catch audio-driven deepfakes.

204K runs

Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.

Input

File URL string

Enter a URL to a video file

Upload video

Drag and drop a video file here, or click to browse

Select File

# window_duration number

Duration (in seconds) of the audio-video segments to analyze.. Default: 2

# sync_threshold number

Score threshold under which a segment is considered out of sync.. Default: 0.3

Output

{
  "segment_scores": [
    {
      "start": 0,
      "end": 2,
      "sync_score": 0.95
    },
    {
      "start": 2,
      "end": 4,
      "sync_score": 0.25
    }
  ],
  "average_sync_score": 0.6
}