AI-Generated Music Detection BETA

Overview

The AI-Generated Music Detection Model can help you determine if a music was entirely generated by an AI model, or if it is a real music. This model was trained on artificially-created and human-created music spanning all sorts of music styles such as pop, rock, electronic, classical, jazz and more.

The Model works by analyzing the acoustic content of the audio. No meta-data is used in the analysis. Tampering with meta-data therefore has no effect on the scoring.

The Model was trained to detect music generated by the main models currently in use: Suno, Udio, Riffusion... Additional models will be added over time as they become available. The model works best on audio files with no vocals.

Use cases

• Music recommendation filtering
• Music tagging and archiving
• Copyright and Royalty tracking
• Content moderation

Related model

The following model can provide a useful complement to the AI-generated music model:

• AI image Detection: Detect AI-generated images.

Use the model

Detect if an audio file was AI-generated

This model is currently gated. Please get in touch for access and implementation details.

The API will then return a JSON response with the ai_generated score. This score is a float between 0 and 1. The higher the value, the higher the confidence that the audio is AI-generated:

                
                
{
    "status": "success",
    "request": {
        "id": "req_0zrbHDeitGYY7wEGncAne",
        "timestamp": 1491402308.4762,
        "operations": 34
    },
    "type": {
      "ai_generated": 0.01
    },
    "media": {
        "id": "med_0zrbk8nlp4vwI5WxIqQ4u",
        "uri": "https://sightengine.com/assets/audio/examples/music.mp3"
    }
}
                
            

Any other needs?

See our full list of Image/Video models for details on other filters and checks you can run on your images and videos. You might also want to check our Text models to moderate text-based content: messages, reviews, comments, usernames...