Zebra Translate
Web API

API Reference for the Zebra Web SDK (zebra-web).

Zebra

class Zebra {}

Class for the Zebra Translate engine.

Zebra.create()

static async function create(
  accessKey: string,
  model: ZebraModel
): Promise<Zebra>

Creates an instance of Zebra Translate engine using .pv file in public directory. Sets the source and target translation languages. The model size is large, hence it will try to use the existing one if it exists, otherwise saves the model in storage.

Parameters

• accessKey string : AccessKey obtained from Picovoice Console.
• model ZebraModel : Object containing Zebra model data.

Returns

• Zebra : An instance of the Zebra engine.

Zebra.translate()

async function translate(text: string): Promise<string>

Translates text. The maximum number of characters that can be translated at once is given by .maxCharacterLimit.

Parameters

• text string : Text to translate.

Returns

• string : Translated text.

Zebra.release()

async function release(): Promise<void>

Releases resources acquired by the Zebra Web SDK.

Zebra.version

get version(): string

Zebra version string.

Zebra.maxCharacterLimit

get maxCharacterLimit(): number

Maximum number of characters accepted by Zebra in one .translate() call.

Zebra.listAvailableDevices()

public static async listAvailableDevices(): Promise<string[]>

Lists all available devices that Zebra can use for inference. Each entry in the list can be the used as the device argument for the .create() method.

Returns

• string[] : List of all available devices that Zebra can use for inference.

ZebraModel

type ZebraModel = {
  base64?: string;
  publicPath?: string;
  customWritePath?: string;
  forceWrite?: boolean;
  version?: number;
}

Zebra model type.

ZebraWorker

class ZebraWorker {}

A class for creating new instances of ZebraWorker.

ZebraWorker.create()

static async create(
  accessKey: string,
  model: ZebraModel,
  device?: string,
): Promise<ZebraWorker>

Creates an instance of ZebraWorker using '.pv' file in public directory. The model size is large, hence it will try to use the existing one if it exists, otherwise saves the model in storage.

Parameters

• accessKey string : AccessKey obtained from Picovoice Console.
• model ZebraModel : Object containing Zebra model data. Sets the source and target translation languages.
• device string? : device String representation of the device (e.g., CPU or GPU) to use. If set to best, the most suitable device is selected automatically. 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.

Returns

• ZebraWorker : An instance of ZebraWorker.

ZebraWorker.translate()

async function translate(text: string): Promise<string>

Translates text. The maximum number of characters that can be translated at once is given by .maxCharacterLimit.

Parameters

• text string : Text to translate.

Returns

• string : Translated text.

ZebraWorker.release()

async function release(): Promise<void>

Releases resources acquired by the Zebra Web SDK.

ZebraWorker.terminate()

async function terminate(): Promise<void>

Force terminates the instance of ZebraWorker.

ZebraWorker.version

get version(): string

Zebra version string.

ZebraWorker.maxCharacterLimit

get maxCharacterLimit(): number

Maximum number of characters accepted by Zebra in one .translate() call.