Leopard Speech-to-Text
Android API

API Reference for the Android Leopard SDK (leopard-android )

package: ai.picovoice.leopard

Leopard

public class Leopard { }

Class for the Leopard Speech-to-Text engine.

Leopard must be initialized using the Builder() Class. Resources should be cleaned when you are done using the delete() function.

Leopard.`delete()`

public void delete()

Releases resources acquired by Leopard.

Leopard.`getSampleRate()`

public int getSampleRate()

Getter for required audio sample rate for PCM data.

Returns

int: Required audio sample rate for PCM data.

Leopard.`getVersion()`

public String getVersion()

Getter for version.

Returns

String: Current Leopard version.

Leopard.`process()`

public LeopardTranscript process(short[] pcm) throws LeopardException

Processes given audio data and returns its transcription. The incoming audio needs to have a sample rate equal to .getSampleRate() 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[] : A frame of audio samples.

Returns

LeopardTranscript: Inferred transcription and word metadata.

Throws

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

Leopard.`processFile()`

public LeopardTranscript processFile(String path) throws LeopardException

Processes a given audio file and returns its transcription.

Parameters

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

Returns

LeopardTranscript: Inferred transcription and word metadata.

Throws

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

Leopard.`Builder`

public static class Builder { }

Builder for creating an instance of Leopard with a mixture of default arguments.

Leopard.Builder.`build()`

public Leopard build(Context context) throws LeopardException

Creates an instance of Leopard Speech-to-Text engine.

Parameters

context Context : The Android app context.

Returns

Leopard: An instance of Leopard Speech-to-Text engine.

Throws

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

Leopard.Builder.`setAccessKey()`

public Leopard.Builder setAccessKey(String accessKey)

Sets the AccessKey of the builder.

Parameters

accessKey String : AccessKey obtained from Picovoice Console .

Returns

Leopard.Builder: Modified Leopard.Builder object.

Leopard.Builder.`setModelPath()`

public Leopard.Builder setModelPath(String modelPath)

Sets the model path of the builder.

Parameters

modelPath String : Path to the file containing model parameters (.pv). Can be either a path that is relative to the project's assets folder or an absolute path to the file on device.

Returns

Leopard.Builder: Modified Leopard.Builder object.

Leopard.Builder.`setEnableAutomaticPunctuation()`

public Leopard.Builder setEnableAutomaticPunctuation(boolean enableAutomaticPunctuation)

Setter for enabling automatic punctuation insertion.

Parameters

enableAutomaticPunctuation boolean : Set to true to enable automatic punctuation insertion.

Returns

Leopard.Builder: Modified Leopard.Builder object.

Leopard.Builder.`setEnableDiarization()`

public Leopard.Builder setEnableDiarization(boolean enableDiarization)

Setter for enabling speaker diarization.

Parameters

enableDiarization boolean : 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

Leopard.Builder: Modified Leopard.Builder object.

LeopardException

public class LeopardException extends Exception { }

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

Exceptions:

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

LeopardTranscript

public class LeopardTranscript {
    public LeopardTranscript(String transcriptString, Word[] wordArray) { }
}

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

Parameters

transcriptString String : Inferred transcription.
wordArray LeopardTranscript.Word[] : Transcribed words and their associated metadata.

LeopardTranscript.`getTranscriptString()`

public String getTranscriptString()

Getter for the inferred transcription.

Returns

String: Inferred transcription.

LeopardTranscript.`getWordArray()`

public Word[] getWordArray()

Getter for transcribed words and their associated metadata.

Returns

LeopardTranscript.Word[]: Transcribed words and their associated metadata.

LeopardTranscript.`Word`

public static class Word {
    public Word(String word, float confidence, float startSec, float endSec, int speakerTag) { }
}

Class for storing word metadata from a LeopardTranscript.

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.