Picovoice Platform — iOS API

API Reference for the iOS Picovoice SDK (Cocoapod)

Picovoice

public class Picovoice { }

Class for Picovoice. Picovoice can be initialized either using the High-level PicovoiceManager() Class or directly using the class constructor. Resources should be cleaned when you are done using the delete() function.

Picovoice.`init()`

init methods for Picovoice.

public init (
    accessKey: String,
    keywordPath: String,
    onWakeWordDetection: @escaping (() -> Void),
    contextPath: String,
    onInference: @escaping ((Inference) -> Void),
    porcupineModelPath: String? = nil,
    porcupineSensitivity: Float32 = 0.5,
    rhinoModelPath: String? = nil,
    rhinoSensitivity: Float32 = 0.5,
    requireEndpoint: Bool = true) throws

Parameters

accessKey String : The AccessKey obtained from Picovoice Console.
keywordPath String : Absolute paths to keyword model file (.ppn).
onWakeWordDetection (() -> Void) : A callback that is invoked upon detection of the keyword.
contextPath String : Absolute path to file containing context parameters (.rhn). A context represents the set of expressions (spoken commands), intents, and intent arguments (slots) within a domain of interest.
onInference (Inference) -> Void) : A callback that is invoked upon completion of intent inference.
porcupineModelPath String? : Absolute path to file containing Porcupine model parameters (.pv).
porcupineSensitivity Float32 : Sensitivities for detecting keywords. Each value should be a number within [0, 1]. A higher sensitivity results in fewer misses at the cost of increasing the false alarm rate.
rhinoModelPath String? : Absolute path to file containing rhino model parameters (.pv).
rhinoSensitivity Float32 : Inference sensitivity. It should be a number within [0, 1]. A higher sensitivity value results in fewer misses at the cost of (potentially)increasing the erroneous inference rate.
requireEndpoint Bool : If set to true, Rhino requires an endpoint (chunk of silence) before finishing inference.

Throws

PicovoiceError: If an error occurs while creating an instance of Picovoice.

Picovoice.`delete()`

Releases resources acquired by Picovoice.

public func delete()

Picovoice.`process()`

Process a frame of audio with the Picovoice platform.

public func process(pcm:[Int16]) throws

Parameters

pcm [Int16] : An array of 16-bit pcm samples.

Throws

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

Picovoice.`frameLength`

Picovoice.frameLength: UInt32

The number of audio samples per frame.

Picovoice.`sampleRate`

Picovoice.sampleRate: UInt32

Audio sample rate accepted by Picovoice.

Picovoice.`version`

Picovoice.version: String

Current Picovoice version.

PicovoiceManager

A High-level iOS binding for Picovoice that handles recording audio from microphone, processes it in real-time, and notifies the client upon detection of the wake word or completion of in voice command inference.

public class PicovoiceManager { }

PicovoiceManager.`init()`

public init(
    accessKey: String,
    keywordPath: String,
    onWakeWordDetection: @escaping (() -> Void),
    contextPath: String,
    onInference: @escaping ((Inference) -> Void),
    porcupineModelPath: String? = nil,
    porcupineSensitivity: Float32 = 0.5,
    rhinoModelPath: String? = nil,
    rhinoSensitivity: Float32 = 0.5,
    requireEndpoint: Bool = true,
    processErrorCallback: ((Error) -> Void)? = nil)

Parameters

accessKey String : The AccessKey obtained from Picovoice Console.
keywordPath String : Absolute paths to keyword model file (.ppn).
onWakeWordDetection (() -> Void) : A callback that is invoked upon detection of the keyword.
contextPath String : Absolute path to file containing context parameters (.rhn). A context represents the set of expressions (spoken commands), intents, and intent arguments (slots) within a domain of interest.
onInference ((Inference) -> Void) : A callback that is invoked upon completion of intent inference.
porcupineModelPath String? : Absolute path to file containing Porcupine model parameters (.pv).
porcupineSensitivity Float32 : Sensitivity for detecting keywords. Each value should be a number within [0, 1]. A higher sensitivity results in fewer misses at the cost of increasing the false alarm rate.
rhinoModelPath String? : Absolute path to file containing rhino model parameters (.pv).
rhinoSensitivity Float32 : Inference sensitivity. It should be a number within [0, 1]. A higher sensitivity value results in fewer misses at the cost of (potentially)increasing the erroneous inference rate.
requireEndpoint Bool : If set to true, Rhino requires an endpoint (chunk of silence) before finishing inference.
processErrorCallback ((Error) -> Void)? = nil) : A callback that is invoked if an error occurs while processing frames. If missing, error will be printed to console.

Throws

PicovoiceError : If an error occurs while creating an instance of Picovoice.

PicovoiceManager.`start()`

public func start() throws

Starts recording audio from the microphone and Picovoice processing loop.

Throws

PicovoiceError : If microphone permission is not granted.

PicovoiceManager.`stop()`

public func stop()

Stop audio recording and processing loop.

PicovoiceError

public class PicovoiceError : LocalizedError { }

Error thrown if an error occurs within Picovoice.

public class PicovoiceMemoryError : PicovoiceError {}
public class PicovoiceIOError : PicovoiceError {}
public class PicovoiceInvalidArgumentError : PicovoiceError {}
public class PicovoiceStopIterationError : PicovoiceError {}
public class PicovoiceKeyError : PicovoiceError {}
public class PicovoiceInvalidStateError : PicovoiceError {}
public class PicovoiceRuntimeError : PicovoiceError {}
public class PicovoiceActivationError : PicovoiceError {}
public class PicovoiceActivationLimitError : PicovoiceError {}
public class PicovoiceActivationThrottledError : PicovoiceError {}
public class PicovoiceActivationRefusedError : PicovoiceError {}