Leopard Speech-to-Text
Node.js API

API Reference for the Node.js Leopard SDK (npm)

Leopard

class Leopard {}

Class for the Leopard Speech-to-Text engine.

Leopard can be initialized using the class constructor(). Resources should be cleaned when you are done using the release() method.

Leopard.constructor()

Leopard.constructor(
  accessKey: string,
  options: LeopardOptions = {}
)

Leopard constructor.

Parameters

• accessKey string : AccessKey obtained from Picovoice Console.
• options LeopardOptions : Optional init configuration arguments.

Returns

• Leopard: An instance of Leopard platform.

Leopard.release()

Leopard.release()

Releases resources acquired by Leopard.

Leopard.sampleRate

Leopard.sampleRate()

Getter for audio sample rate accepted by Leopard.

Returns

• number: Audio sample rate accepted by Leopard.

Leopard.version

Leopard.version()

Getter for version.

Returns

• string: Current Leopard version.

Leopard.process()

Leopard.process(pcm)

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

• pcm Array<number> : Audio data.

Returns

• LeopardTranscript: Inferred transcription.

Leopard.processFile()

Leopard.processFile(audioPath)

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

Parameters

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

Returns

• LeopardTranscript: Inferred transcription.

Leopard.listAvailableDevices()

Leopard.listAvailableDevices(options: LeopardInputOptions = {}): string[]

Lists all available devices that Leopard can use for inference. Each entry in the list can be the device argument of the constructor.

Parameters

• options LeopardInputOptions : Optional input configuration arguments.

Returns

• string[] : List of all available devices that Leopard can use.

LeopardOptions

type LeopardOptions = {
  modelPath?: string;
  device?: string;
  libraryPath?: string;
  enableAutomaticPunctuation?: boolean;
  enableDiarization?: boolean;
};

Leopard init options type.

• modelPath string : Path to the file containing model parameters (.pv).
• device string? : String representation of the device (e.g., CPU or GPU) to use for inference. If set to best, picoLLM picks the most suitable device. If set to gpu, the engine uses the first available GPU device. To select a specific GPU device, set this argument to gpu:${GPU_INDEX}, where ${GPU_INDEX} is the index of the target GPU. If set to cpu, the engine will run on the CPU with the default number of threads. To specify the number of threads, set this argument to cpu:${NUM_THREADS}, where ${NUM_THREADS} is the desired number of threads.
• libraryPath string : Path to the Leopard dynamic library (.node).
• enableAutomaticPunctuation boolean : Whether to enable automatic punctuation. Default is false.
• 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 speaker_tag to identify unique speakers.

LeopardInputOptions

type LeopardInputOptions = {
  libraryPath?: string;
};

Leopard input options type.

• libraryPath string : Path to the Leopard dynamic library (.node).

LeopardWord

LeopardWord

Object which contains a transcribed word 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 : The 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.

LeopardTranscript

LeopardTranscript

Object which contains the transcription results of the engine:

• transcript string : Inferred transcription.
• words LeopardWord[] : transcribed words and its associated metadata.

Errors

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

Exceptions:

class PvStatusOutOfMemoryError        extends Error {}
class PvStatusIoError                 extends Error {}
class PvStatusInvalidArgumentError    extends Error {}
class PvStatusStopIterationError      extends Error {}
class PvStatusKeyError                extends Error {}
class PvStatusInvalidStateError       extends Error {}
class PvStatusRuntimeError            extends Error {}
class PvStatusActivationError         extends Error {}
class PvStatusActivationLimitReached  extends Error {}
class PvStatusActivationThrottled     extends Error {}
class PvStatusActivationRefused       extends Error {}