Cheetah - iOS API

API Reference for the iOS Cheetah SDK (Cocoapod)

Cheetah

public class Cheetah { }

Class for the Cheetah Speech-to-Text engine. Resources should be cleaned when you are done using the delete() function.

Cheetah.`init()`

init method for Cheetah Speech-to-Text engine with a mixture of arguments.

public init(accessKey: String, modelPath: String, endpointDuration: Float = 1.0) throws -> Cheetah

Parameters

accessKey String : The AccessKey obtained from Picovoice Console.
modelPath String : Absolute path to file containing model parameters (.pv).
endpointDuration [Float32]? : Duration of endpoint in seconds. A speech endpoint is detected when there is a chunk of audio (with a duration specified herein) after an utterance without any speech in it. Set duration to 0 to disable this. Default is 1 second.

Throws

CheetahError: If an error occurs while creating an instance of Cheetah Speech-to-Text engine.

public init(accessKey: String, modelURL: URL, endpointDuration: Float = 1.0) throws -> Cheetah

Parameters

accessKey String : The AccessKey obtained from Picovoice Console.
modelURL URL : URL to file containing model parameters (.pv).
endpointDuration [Float32]? : Duration of endpoint in seconds. A speech endpoint is detected when there is a chunk of audio (with a duration specified herein) after an utterance without any speech in it. Set duration to 0 to disable this. Default is 1 second.

Throws

CheetahError: If an error occurs while creating an instance of Cheetah Speech-to-Text engine.

Cheetah.`delete()`

Releases resources acquired by the Cheetah engine.

public func delete()

Cheetah.`process()`

Process a frame of audio with the Cheetah Speech-to-Text engine.

public func process(pcm:[Int16]) throws -> (String, Bool)

Parameters

pcm [Int16] : The number of samples per frame can be attained by calling Cheetah.frameLength. The incoming audio needs to have a sample rate equal to Cheetah.sampleRate and be 16-bit linearly-encoded. Furthermore, Cheetah operates on single-channel audio.

Returns

(String, bool) : Tuple of any newly-transcribed speech (if none is available then an empty string is returned) and a flag indicating if an endpoint has been detected.

Throws

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

Cheetah.`flush()`

Marks the end of the audio stream, flushes internal state of the object, and returns any remaining transcribed text.

public func flush() throws -> String

Returns

String : Any remaining transcribed text. If none is available then an empty string is returned.

Throws

CheetahError: If there is an error while processing.

Cheetah.`frameLength`

Cheetah.frameLength: UInt32

The number of audio samples per frame.

Cheetah.`sampleRate`

Cheetah.sampleRate: UInt32

Audio sample rate accepted by Cheetah.

Cheetah.`version`

Cheetah.version: String

Current Cheetah version.

CheetahError

public class CheetahError : LocalizedError { }

Error thrown if an error occurs within Cheetah Speech-to-Text engine.

public class CheetahMemoryError : CheetahError {}
public class CheetahIOError : CheetahError {}
public class CheetahInvalidArgumentError : CheetahError {}
public class CheetahStopIterationError : CheetahError {}
public class CheetahKeyError : CheetahError {}
public class CheetahInvalidStateError : CheetahError {}
public class CheetahRuntimeError : CheetahError {}
public class CheetahActivationError : CheetahError {}
public class CheetahActivationLimitError : CheetahError {}
public class CheetahActivationThrottledError : CheetahError {}
public class CheetahActivationRefusedError : CheetahError {}