Skip to main content

Authenticity Verification: start task

POST 

/api/technology/experimental/authenticity-verification

Experimental feature

Please note that Authenticity Verification is an experimental feature.
It is under development and may change in the future.

Start an Authenticity Verification task for a media file.

Authenticity Verification features

The Authenticity Verification endpoint supports the following independent operations:

  • Deepfake Detection
  • Audio Manipulation Detection
  • Replay Attack Detection

Be default, all operations are performed, and they are billed together as one Authenticity Verification task. It is possible to specify the list of requested operations (deepfake_detection, audio_manipulation_detection, replay_attack_detection) to save computational resources.

Features of all the operations

  • Multi-channel media files are supported.
  • For each channel an independent operation's result is produced.
  • Processing can be limited to a specific time segment in the media file with query parameters.

Deepfake Detection specific features

  • If there is less than 3 seconds of audio in a processed channel (or time segment), the score will be empty (i.e. null).

Audio Manipulation Detection specific features

  • Under the hood, the technology analyzes overlapping segments of 400 ms. By default, additional logic is applied to the raw segments, joining adjacent suspicious segments into one to improve the usability of the results. To obtain the raw segmentation instead, use the raw_segmentation=True query parameter.

Request

Responses

Authenticity Verification task was accepted. Follow the Location header to poll for the task state.

Response Headers
    X-Location

    ⚠️ Deprecated - use Location header instead.

    Example: /api/technology/authenticity-verification/123e4567-e89b-12d3-a456-426614174000
    Location

    A URL the client should poll for task state and result.

    Example: /api/technology/authenticity-verification/123e4567-e89b-12d3-a456-426614174000