Synthetic voice detection

This module is dedicated to classifying AI-produced audio content, specifically centering on Synthetic Speech Detection for AI-generated vocals.

Documentation

Settings

  • Name
    threshold
    Type
    number
    Description

    Threshold defines the model sensitivity.

Input

  • Name
    inputUrl
    Type
    string
    Description

    Audio to be classified.

Output

  • Name
    class
    Type
    string
    Description

    Prediction result

  • Name
    timeline
    Type
    string
    Description

    Timeline of predictions, for each window of input audio.

Related Modules

Ready to take your project to the next level?

Start now — or reach out for assistance.

Get startedContact sales