<!--
{
  "availability" : [
    "iOS: 15.0.0 -",
    "iPadOS: 15.0.0 -",
    "macCatalyst: 15.0.0 -",
    "macOS: 12.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLSoundClassifier/predictions(from:overlapFactor:predictionTimeWindowSize:)",
  "metadataVersion" : "0.1.0",
  "role" : "Instance Method",
  "symbol" : {
    "kind" : "Instance Method",
    "modules" : [
      "Create ML"
    ],
    "preciseIdentifier" : "s:8CreateML17MLSoundClassifierV11predictions4from13overlapFactor24predictionTimeWindowSizeSaySSGSay10Foundation3URLVG_S2dtKF"
  },
  "title" : "predictions(from:overlapFactor:predictionTimeWindowSize:)"
}
-->

# predictions(from:overlapFactor:predictionTimeWindowSize:)

Generates predictions that use an overlap factor and time window size for an array of audio files.

```
func predictions(from audioFiles: [URL], overlapFactor: Double, predictionTimeWindowSize: TimeInterval) throws -> [String]
```

## Parameters

`audioFiles`

An array of audio-file URLs you want the sound classifier to categorize.

`overlapFactor`

The amount of overlap between successive analysis windows when the model analyzes a block of
audio data.

`predictionTimeWindowSize`

The duration of the audio buffer the method sends to the model for each
prediction.

## Return Value

An array of prediction labels for the audio files.

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)