Leopard Speech-to-Text
React Native API

API Reference for the React Native Leopard SDK (npm)

Leopard

class Leopard { }

Class for the Leopard Speech-to-Text engine.

Leopard.create()

public static async create(
  accessKey: string,
  modelPath: string,
  options: LeopardOptions = {}
): Promise<Leopard>

Leopard constructor.

Parameters

• accessKey string : AccessKey obtained from Picovoice Console.
• modelPath string : Path to the file containing model parameters (.pv). Can be either a path that is relative to the assets/resource folder or an absolute path to the file on device.
• options LeopardOptions : Optional configuration arguments:
  • enableAutomaticPunctuation boolean : Whether to enable automatic punctuation.
  • enableDiarization boolean : Whether to enable diarization. Set to true to enable speaker diarization, which allows Leopard to differentiate speakers as part of the transcription process. Word metadata will include a speakerTag to identify unique speakers.

Returns

• Promise<Leopard>: An instance of Leopard platform.

Leopard.delete()

async delete()

Releases resources acquired by Leopard.

Leopard.sampleRate

get sampleRate()

Getter for audio sample rate accepted by Leopard.

Returns

• number: Audio sample rate accepted by Leopard.

Leopard.version

get version()

Getter for version.

Returns

• string: Current Leopard version.

Leopard.process()

async process(frame: number[]): Promise<LeopardTranscript>

Processes given audio data with the speech-to-text engine. The incoming audio needs to have a sample rate equal to .sampleRate and be 16-bit linearly-encoded. Leopard operates on single-channel audio.

Parameters

• frame number[] : A frame of audio samples.

Returns

• Promise<LeopardTranscript>: LeopardTranscript object which contains the transcription results of the engine.

Leopard.processFile()

async processFile(audioPath: string): Promise<string>

Processes an audio file with the speech-to-text engine.

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

• Promise<LeopardTranscript>: LeopardTranscript object which contains the transcription results of the engine.

LeopardError

class LeopardError extends Error { }

Exception thrown if an error occurs within Leopard Speech-to-Text engine.

Exceptions:

class LeopardActivationError           extends LeopardError { }
class LeopardActivationLimitError      extends LeopardError { }
class LeopardActivationRefusedError    extends LeopardError { }
class LeopardActivationThrottledError  extends LeopardError { }
class LeopardIOError                   extends LeopardError { }
class LeopardInvalidArgumentError      extends LeopardError { }
class LeopardInvalidStateError         extends LeopardError { }
class LeopardKeyError                  extends LeopardError { }
class LeopardMemoryError               extends LeopardError { }
class LeopardRuntimeError              extends LeopardError { }
class LeopardStopIterationError        extends LeopardError { }

LeopardOptions

type LeopardOptions = {
  enableAutomaticPunctuation?: boolean;
  enableDiarization?: boolean;
}

Class containing optional configuration parameters for Leopard.

• enableAutomaticPunctuation boolean : Flag to enable automatic punctuation insertion.
• enableDiarization boolean : Flag to enable diarization.

LeopardTranscript

type LeopardTranscript = {
  transcript: string;
  words: LeopardWord[];
}

Class containing results from a Leopard process function.

• transcript string : Inferred transcription.
• words LeopardWord[] : Transcribed words and their associated metadata.

LeopardWord

type LeopardWord = {
  word: string;
  startSec: number;
  endSec: number;
  confidence: number;
  speakerTag: number;
}

Class containing results word transcribed by Leopard and their associated metadata.

• word string : Transcribed word.
• startSec number : Start of word in seconds.
• endSec number : End of word in seconds.
• confidence number : Transcription confidence. It is a number within [0, 1].
• speakerTag number : Speaker tag is -1 if diarization is not enabled during initialization; otherwise, it's a non-negative integer identifying unique speakers, with 0 reserved for unknown speakers.