Falcon Speaker Diarization
iOS API

API Reference for the iOS Falcon SDK (Cocoapod)

Falcon

public class Falcon { }

Class for the Falcon Speaker Diarization engine. Resources should be cleaned when you are done using the delete() function.

Falcon.init()

init method for Falcon Speaker Diarization engine.

public init(accessKey: String, modelPath:String? = nil) throws -> Falcon

Parameters

• accessKey String : The AccessKey obtained from Picovoice Console.
• modelPath String? : Absolute path to file containing model parameters (.pv).

Throws

• FalconError: If an error occurs while creating an instance of Falcon Speaker Diarization engine.

public init(accessKey: String, modelURL: URL, enableAutomaticPunctuation: Bool = false) throws -> Falcon

Falcon.delete()

Releases resources acquired by the Falcon engine.

public func delete()

Falcon.process()

Processes given audio data with the Falcon Speaker Diarization engine.

public func process(pcm: [Int16]) throws -> ([FalconSegment])

Parameters

• pcm [Int16] : The incoming audio needs to have a sample rate equal to Falcon.sampleRate and be 16-bit linearly-encoded. Furthermore, Falcon operates on single-channel audio.

Returns

• [FalconSegment] : Sequence of speaker segments with their associated metadata.

Throws

• FalconError: If there is an error while processing the audio frame.

Falcon.processFile()

Processes a given audio file with the Falcon Speaker Diarization engine.

public func processFile(audioPath: String) throws -> ([FalconSegment])

Parameters

• audioPath String : Absolute path to the audio file. The supported formats are: 3gp (AMR), FLAC, MP3, MP4/m4a (AAC), Ogg, WAV and WebM.

Returns

• [FalconSegment] : Sequence of speaker segments with their associated metadata.

Throws

• FalconError: If there is an error while processing the audio frame.

Falcon.processFile()

Processes a given audio file with the Falcon Speaker Diarization engine.

public func processFile(audioURL: URL) throws -> ([FalconSegment])

Parameters

• audioURL URL : URL of the audio file. The supported formats are: 3gp (AMR), FLAC, MP3, MP4/m4a (AAC), Ogg, WAV and WebM.

Returns

• [FalconSegment] : Sequence of speaker segments with their associated metadata.

Throws

• FalconError: If there is an error while processing the audio frame.

Falcon.sampleRate

public static let sampleRate: UInt32

Audio sample rate accepted by Falcon.

Falcon.version

public static let version: String

Current Falcon version.

FalconError

public class FalconError : LocalizedError { }

Error thrown if an error occurs within Falcon Speaker Diarization engine.

public class FalconMemoryError : FalconError {}
public class FalconIOError : FalconError {}
public class FalconInvalidArgumentError : FalconError {}
public class FalconStopIterationError : FalconError {}
public class FalconKeyError : FalconError {}
public class FalconInvalidStateError : FalconError {}
public class FalconRuntimeError : FalconError {}
public class FalconActivationError : FalconError {}
public class FalconActivationLimitError : FalconError {}
public class FalconActivationThrottledError : FalconError {}
public class FalconActivationRefusedError : FalconError {}

FalconSegment

public struct FalconSegment { }

Struct for storing segment metadata returned from the Falcon engine.

FalconSegment.startSec

FalconSegment.startSec: Float

Start of segment in seconds.

FalconSegment.endSec

FalconSegment.endSec: Float

End of segment in seconds.

FalconSegment.speakerTag

FalconSegment.speakerTag: Int

Speaker tag is a non-negative integer identifying unique speakers.