Class AudioToTextExecutionSettings.Builder
- java.lang.Object
-
- com.microsoft.semantickernel.services.audio.AudioToTextExecutionSettings.Builder
-
- Enclosing class:
- AudioToTextExecutionSettings
public static class AudioToTextExecutionSettings.Builder extends Object
Represents a builder for audio to text execution settings.
-
-
Constructor Summary
Constructors Constructor Description Builder()
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description AudioToTextExecutionSettingsbuild()Builds the audio to text execution settings.AudioToTextExecutionSettings.BuilderwithDeploymentName(String deploymentName)Sets the deployment name to use for audio transcription.AudioToTextExecutionSettings.BuilderwithFilename(String filename)Sets the filename or descriptive identifier to associate with the audio data.AudioToTextExecutionSettings.BuilderwithLanguage(String language)The language of the audio data as two-letter ISO-639-1 language code (e.g.AudioToTextExecutionSettings.BuilderwithPrompt(String prompt)An optional hint to guide the model's style or continue from a prior audio segment.AudioToTextExecutionSettings.BuilderwithResponseFormat(String responseFormat)The requested format of the transcription response data, which will influence the content and detail of the result.AudioToTextExecutionSettings.BuilderwithTemperature(Double temperature)The randomness of the generated text.
-
-
-
Method Detail
-
withDeploymentName
public AudioToTextExecutionSettings.Builder withDeploymentName(String deploymentName)
Sets the deployment name to use for audio transcription.- Parameters:
deploymentName- The deployment name.- Returns:
- The builder.
-
withFilename
public AudioToTextExecutionSettings.Builder withFilename(String filename)
Sets the filename or descriptive identifier to associate with the audio data.- Parameters:
filename- The filename or descriptive identifier.- Returns:
- The builder.
-
withResponseFormat
public AudioToTextExecutionSettings.Builder withResponseFormat(String responseFormat)
The requested format of the transcription response data, which will influence the content and detail of the result.- Parameters:
responseFormat- The response format. Supported formats are json, text, srt, verbose_json, or vtt. Default is 'json'.- Returns:
- The builder.
-
withLanguage
public AudioToTextExecutionSettings.Builder withLanguage(String language)
The language of the audio data as two-letter ISO-639-1 language code (e.g. 'en' or 'es').- Parameters:
language- The language of the audio data.- Returns:
- The builder.
-
withPrompt
public AudioToTextExecutionSettings.Builder withPrompt(String prompt)
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.- Parameters:
prompt- The prompt.- Returns:
- The builder.
-
withTemperature
public AudioToTextExecutionSettings.Builder withTemperature(Double temperature)
The randomness of the generated text. Select a value from 0.0 to 1.0. 0 is the default.- Parameters:
temperature- The temperature.- Returns:
- The builder.
-
build
public AudioToTextExecutionSettings build()
Builds the audio to text execution settings.- Returns:
- The audio to text execution settings.
-
-