# SNClassifySoundRequest A request that classifies sound using a Core ML model. ``` class SNClassifySoundRequest ``` ## Overview An `SNClassifySoundRequest` represents a specific sound classification model. Analyze audio data with a sound classification model by: 1. Creating an `SNClassifySoundRequest`, either with the Sound Analysis model, or by providing your custom Core ML model. 2. Adding the sound request to an [`SNAudioFileAnalyzer`](/documentation/SoundAnalysis/SNAudioFileAnalyzer) or [`SNAudioStreamAnalyzer`](/documentation/SoundAnalysis/SNAudioStreamAnalyzer) to process an audio file or stream, respectively. ```swift func makeRequest(_ customModel: MLModel? = nil) throws -> SNClassifySoundRequest { // If applicable, create a request with a custom sound classification model. if let model = customModel { let customRequest = try SNClassifySoundRequest(mlModel: model) return customRequest } // Create a request with the Sound Analysis model. let version1 = SNClassifierIdentifier.version1 let request = try SNClassifySoundRequest(classifierIdentifier: version1) return request } let classifySoundRequest = try makeRequest() // Prints every label in the request's sound classification model. print(classifySoundRequest.knownClassifications) ``` For more information about creating and using classify sound requests, see: - [Classifying Sounds in an Audio File](/documentation/SoundAnalysis/classifying-sounds-in-an-audio-file) - [Classifying Sounds in an Audio Stream](/documentation/SoundAnalysis/classifying-sounds-in-an-audio-stream) ## Topics ### Creating a Request [`init(mlModel:)`](/documentation/SoundAnalysis/SNClassifySoundRequest/init(mlModel:)-6rmee) Creates a request that uses a custom sound classification model. [`init(classifierIdentifier:)`](/documentation/SoundAnalysis/SNClassifySoundRequest/init(classifierIdentifier:)) Creates a request that uses the framework’s built-in sound classification model. [`SNClassifierIdentifier`](/documentation/SoundAnalysis/SNClassifierIdentifier) An identifier that represents the versions of the framework’s sound classifier. ### Configuring a Request [`overlapFactor`](/documentation/SoundAnalysis/SNClassifySoundRequest/overlapFactor) The amount of overlap between successive analysis windows when the model operates on a fixed-size audio block. [`windowDuration`](/documentation/SoundAnalysis/SNClassifySoundRequest/windowDuration) The duration of the audio buffer the request sends to the underlying sound classifier for each prediction. ### Inspecting a Request [`knownClassifications`](/documentation/SoundAnalysis/SNClassifySoundRequest/knownClassifications) A string array that contains every prediction label in the request’s underlying sound classifier model. [`SNTimeDurationConstraint`](/documentation/SoundAnalysis/SNTimeDurationConstraint-swift.enum) Defines the time duration windows the request’s underlying sound classifier accepts with a range, or an array, of durations. [`SNTimeDurationConstraint`](/documentation/SoundAnalysis/SNTimeDurationConstraint-c.class) Defines the time duration windows the request’s underlying sound classifier accepts with a range, or an array, of durations. ### Instance Properties [`windowDurationConstraint`](/documentation/SoundAnalysis/SNClassifySoundRequest/windowDurationConstraint-5no60) A range or list of sound duration times the request’s underlying sound classifier supports. [`windowDurationConstraint`](/documentation/SoundAnalysis/SNClassifySoundRequest/windowDurationConstraint-5aqvx) A range or list of sound duration times the request’s underlying sound classifier supports. [`SNTimeDurationConstraint`](/documentation/SoundAnalysis/SNTimeDurationConstraint-c.class) Defines the time duration windows the request’s underlying sound classifier accepts with a range, or an array, of durations. --- Copyright © 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)