Package com.microsoft.semantickernel.services.audio

Class AudioToTextExecutionSettings

java.lang.Object

com.microsoft.semantickernel.services.audio.AudioToTextExecutionSettings

public class AudioToTextExecutionSettings
extends Object

Represents audio content.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	AudioToTextExecutionSettings.Builder	Represents a builder for audio to text execution settings.

Constructor Summary

Constructors

Constructor	Description
AudioToTextExecutionSettings(String deploymentName, String filename, String responseFormat, String language, String prompt, Double temperature)	Creates an instance of audio to text execution settings.

Method Summary

Modifier and Type	Method	Description
static AudioToTextExecutionSettings.Builder	builder()	Creates a new builder.
String	getDeploymentName()	The deployment name to use for audio transcription.
String	getFilename()	The optional filename or descriptive identifier to associate with the audio data.
String	getLanguage()	The language of the audio data as two-letter ISO-639-1 language code (e.g.
String	getPrompt()	An optional hint to guide the model's style or continue from a prior audio segment.
String	getResponseFormat()	The requested format of the transcription response data, which will influence the content and detail of the result.
Double	getTemperature()	The randomness of the generated text.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

AudioToTextExecutionSettings

public AudioToTextExecutionSettings(@Nullable
                                    String deploymentName,
                                    @Nullable
                                    String filename,
                                    String responseFormat,
                                    @Nullable
                                    String language,
                                    @Nullable
                                    String prompt,
                                    @Nullable
                                    Double temperature)

Creates an instance of audio to text execution settings.

Parameters:

deploymentName - The deployment name.

filename - The filename.

responseFormat - The response format.

language - The language.

prompt - The prompt.

temperature - The temperature.

Method Detail

getDeploymentName

@Nullable
public String getDeploymentName()

The deployment name to use for audio transcription.

When making a request against Azure OpenAI, this should be the customizable name of the "model deployment" (example: my-gpt4-deployment) and not the name of the model itself (example: gpt-4).

When using non-Azure OpenAI, this corresponds to "model" in the request options and should use the appropriate name of the model (example: gpt-4).

Returns:

The deployment name.

getFilename

@Nullable
public String getFilename()

The optional filename or descriptive identifier to associate with the audio data.

Returns:

The filename or descriptive identifier.

getResponseFormat

public String getResponseFormat()

The requested format of the transcription response data, which will influence the content and detail of the result.

Returns:

The response format.

getLanguage

@Nullable
public String getLanguage()

The language of the audio data as two-letter ISO-639-1 language code (e.g. 'en' or 'es').

Returns:

The language of the audio data.

getPrompt

@Nullable
public String getPrompt()

An optional hint to guide the model's style or continue from a prior audio segment. The written language of the prompt should match the primary spoken language of the audio data.

Returns:

The prompt.

getTemperature

@Nullable
public Double getTemperature()

The randomness of the generated text. Select a value from 0.0 to 1.0. 0 is the default.

Returns:

The temperature.

builder

public static AudioToTextExecutionSettings.Builder builder()

Creates a new builder.

Returns:

The builder.