Leopard Speech-to-Text — Go API

API Reference for the Leopard Go SDK (pkg.go.dev)

leopard.SampleRate

var SampleRate int

Audio sample rate accepted by Leopard.

leopard.Version

var Version string

Leopard version.

leopard.Leopard

type Leopard struct

Struct for the Leopard Speech-to-Text engine.

leopard.Leopard.AccessKey

var AccessKey string

AccessKey obtained from Picovoice Console (https://console.picovoice.ai/).

leopard.Leopard.ModelPath

var ModelPath string

Absolute path to the file containing model parameters.

leopard.Leopard.LibraryPath

var LibraryPath string

Absolute path to Leopard's dynamic library.

leopard.Leopard.EnableAutomaticPunctuation

var EnableAutomaticPunctuation bool

Flag to enable automatic punctuation insertion.

leopard.Leopard.Delete()

func (leopard *Leopard) Delete() error

Releases resources acquired by Leopard.

Returns

• error : Error produced by the Leopard SDK. nil if no error was encountered.

leopard.Leopard.Init()

func (leopard *Leopard) Init() error

Init function for Leopard. Must be called before attempting process.

Returns

• error : Error produced by the Leopard SDK. nil if no error was encountered.

leopard.Leopard.Process()

func (leopard *Leopard) Process(pcm []int16) (string, []LeopardWord, error)

Processes a given audio data and returns its transcription. The audio needs to have a sample rate equal to .SampleRate and be 16-bit linearly-encoded. This function operates on single-channel audio. If you wish to process data in a different sample rate or format consider using ProcessFile. Returns the inferred transcription.

Returns

• string : Transcription for the given audio.
• []LeopardWord : List of words in the transcription and their associated metadata.
• error : Error produced by the Leopard SDK. nil if no error was encountered.

leopard.Leopard.ProcessFile()

func (leopard *Leopard) ProcessFile(audioPath string) (string, []LeopardWord, error)

Processes a given audio file and returns its transcription. The file needs to have a sample rate equal to or greater than .SampleRate. The supported formats are: FLAC, MP3, Ogg, Opus, Vorbis, WAV, and WebM. Returns the inferred transcription.

Returns

• string : Transcription for the given audio file.
• []LeopardWord : List of words in the transcription and their associated metadata.
• error : Error produced by the Leopard SDK. nil if no error was encountered.

leopard.NewLeopard()

func NewLeopard(accessKey string) Leopard

Creates a Leopard struct with default parameters.

Parameters

• accessKey string : AccessKey obtained from Picovoice Console (https://console.picovoice.ai/).

Returns

• Leopard : An instance of Leopard struct.

LeopardWord

type LeopardWord struct {
    Word string
    StartSec float32
    EndSec float32
    Confidence float32
}

Struct 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].

leopard.LeopardError

type LeopardError struct

Custom error type for errors produced from the Leopard Go SDK.

leopard.LeopardError.Error()

func (e *LeopardError) Error() string

Formats the Leopard error into a string.

Returns

• string : Formatted error string.

leopard.PvStatus

type PvStatus struct

Status return codes from the Leopard library. Possible values are:

const (
    SUCCESS                  PvStatus = 0
    OUT_OF_MEMORY            PvStatus = 1
    IO_ERROR                 PvStatus = 2
    INVALID_ARGUMENT         PvStatus = 3
    STOP_ITERATION           PvStatus = 4
    KEY_ERROR                PvStatus = 5
    INVALID_STATE            PvStatus = 6
    RUNTIME_ERROR            PvStatus = 7
    ACTIVATION_ERROR         PvStatus = 8
    ACTIVATION_LIMIT_REACHED PvStatus = 9
    ACTIVATION_THROTTLED     PvStatus = 10
    ACTIVATION_REFUSED       PvStatus = 11
)