Leopard Speech-to-Text
.NET API

API Reference for the .NET Leopard SDK (NuGet)

namespace: Pv

Leopard

public class Leopard : IDisposable { }

Class for the Leopard Speech-to-Text engine.

Leopard.Create()

public static Leopard Create(
    string accessKey,
    string modelPath,
    string device = null,
    bool enableAutomaticPunctuation = false,
    bool enableDiarization = false)

Leopard constructor.

Parameters

• accessKey string : AccessKey obtained from Picovoice Console.
• modelPath string : Absolute path to the file containing model parameters (.pv).
• device string : 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.
• enableAutomaticPunctuation bool : Whether to enable automatic punctuation.
• enableDiarization bool : 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.

Returns

• Leopard: An instance of Leopard Speech-To-Text engine.

Throws

• LeopardException: If an error occurs while creating an instance of the Leopard Speech-to-Text engine.

Leopard.Process()

public LeopardTranscript Process(Int16[] pcm)

Processes given audio data and returns its transcription. The incoming audio needs to have a sample rate equal to .SampleRate() and be 16-bit linearly-encoded. Furthermore, Leopard operates on single channel audio. If you wish to process data in a different sample rate or format consider using .ProcessFile().

Parameters

• pcm short[] : Audio data.

Returns

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

Throws

• LeopardException: if there is an error while processing the audio frame.

Leopard.ProcessFile()

public LeopardTranscript ProcessFile(string audioPath)

Processes a given audio file and returns its transcription.

Parameters

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

Returns

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

Throws

• LeopardException: if there is an error while processing the audio file.

Leopard.SampleRate

public int SampleRate { get; private set; }

Getter for audio sample rate accepted by Picovoice.

Returns

• int: Audio sample rate accepted by Picovoice.

Leopard.Version

public string Version { get; private set; }

Getter for version.

Returns

• string: Current Leopard version.

Leopard.GetAvailableDevices()

public static string[] GetAvailableDevices()

Retrieves a list of hardware devices that can be specified when constructing Leopard.

Returns

• string[]: An array of available hardware devices.

Throws

• LeopardException: If an error occurs while retrieving the hardware devices.

LeopardTranscript

public class LeopardTranscript {
    public LeopardTranscript(string transcriptString, LeopardWord[] wordArray)
}

Class that contains transcription results returned from Leopard.process() and Leopard.processFile().

Parameters

• transcriptString String : Inferred transcription.
• wordArray LeopardWord[] : Transcribed words and their associated metadata.

LeopardTranscript.TranscriptString

public string TranscriptString { }

Getter for the inferred transcription.

Returns

• String: Inferred transcription.

LeopardTranscript.WordArray

public LeopardWord[] WordArray { }

Getter for transcribed words and their associated metadata.

Returns

• LeopardWord[]: Transcribed words and their associated metadata.

LeopardWord

public class LeopardWord{
    public LeopardWord(string word, float confidence, float startSec, float endSec, int speakerTag)
}

Class for storing word metadata.

Parameters

• word String : Transcribed word.
• confidence float : Transcription confidence. It is a number within [0, 1].
• startSec float : Start of word in seconds.
• endSec float : End of word in seconds.
• speakerTag int : 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.

LeopardWord.Word

public string Word { get; private set; }

Getter for the transcribed word.

Returns

• String: Transcribed word.

LeopardWord.Confidence

public float Confidence { get; private set; }

Getter for the transcription confidence.

Returns

• float: Transcription confidence. It is a number within [0, 1].

LeopardWord.StartSec

public float StartSec { get; private set; }

Getter for the start of word in seconds.

Returns

• float: Start of word in seconds.

LeopardWord.EndSec

public float EndSec { get; private set; }

Getter for the end of word in seconds.

Returns

• float: End of word in seconds.

LeopardWord.SpeakerTag

public int SpeakerTag { get; private set; }

Getter for the speaker tag.

Returns

• int: Speaker tag associated with speaker.

LeopardException

public class LeopardException : Exception

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

Exceptions:

public class LeopardActivationException           : LeopardException { }
public class LeopardActivationLimitException      : LeopardException { }
public class LeopardActivationRefusedException    : LeopardException { }
public class LeopardActivationThrottledException  : LeopardException { }
public class LeopardIOException                   : LeopardException { }
public class LeopardInvalidArgumentException      : LeopardException { }
public class LeopardInvalidStateException         : LeopardException { }
public class LeopardKeyException                  : LeopardException { }
public class LeopardMemoryException               : LeopardException { }
public class LeopardRuntimeException              : LeopardException { }
public class LeopardStopIterationException        : LeopardException { }