Skip to main content
Version: 4.0.0-rc1

Authenticity Verification

The Authenticity Verification technology determines whether a media file contains a deepfaked or real voice.

This page explains how to use Phonexia Authenticity Verification in our web application. If you want to dive deeper into the inner workings of this technology, check out our detailed technical documentation.

Uploading files​

Phonexia provides several audio examples to help you explore how Authenticity Verification works. Currently, uploading your own files or creating new recordings is not available.

Results​

After uploading your recordings, they will appear in the left panel. Once processing is complete, the confidence score will be displayed in the right panel. The results are displayed in a range from -2 to 6. Positive (red) values indicate a deepfake, while negative (green) values signify an authentic voice.

Export formats​

Once your results are ready, you can export them in various formats.

Authenticity Verification results can be exported individually for each file in CSV, XLSX, or JSON format. Each export file is named after the corresponding audio file and includes the channel number as well as the deepfake confidence (confidence score).

The same results can also be exported in bulk as a ZIP file. Additionally, users have the option to export a summary file that displays the scores for all the selected recordings.

XLSX format​

Table showing channel information and the respective deepfake confidence scores.

CSV format​

Channel,Deepfake Confidence
0,-0.76

JSON format​

{
  "deepfake_detection": {
    "channels": [
      {
        "channel_number": 0,
        "score": -0.76397834777832
      }
    ]
  }
}

All results​

Whether in CSV or XLSX format, the export file displays the deepfake confidence for each selected recording.

Table showing filename, channel, and the respective deepfake confidence scores.