共用方式為

AudioTranscriptionOptions Class

  • Reference
Package:
com.azure.ai.openai.models
Maven Artifact:
com.azure:azure-ai-openai:1.0.0-beta.13
  • java.lang.Object
    • com.azure.ai.openai.models.AudioTranscriptionOptions

public final class AudioTranscriptionOptions

The configuration information for an audio transcription request.

Constructor Summary

Constructor Description
AudioTranscriptionOptions(byte[] file)

Creates an instance of AudioTranscriptionOptions class.

Method Summary

Modifier and Type Method and Description
byte[] getFile()

Get the file property: The audio data to transcribe.
String getFilename()

Get the filename property: The optional filename or descriptive identifier to associate with with the audio data.
String getLanguage()

Get the language property: The primary spoken language of the audio data to be transcribed, supplied as a two-letter ISO-639-1 language code such as 'en' or 'fr'.
String getModel()

Get the model property: The model to use for this transcription request.
String getPrompt()

Get the prompt property: An optional hint to guide the model's style or continue from a prior audio segment.
AudioTranscriptionFormat getResponseFormat()

Get the responseFormat property: The requested format of the transcription response data, which will influence the content and detail of the result.
Double getTemperature()

Get the temperature property: The sampling temperature, between 0 and 1.
List<AudioTranscriptionTimestampGranularity> getTimestampGranularities()

Get the timestampGranularities property: The timestamp granularities to populate for this transcription.
AudioTranscriptionOptions setFilename(String filename)

Set the filename property: The optional filename or descriptive identifier to associate with with the audio data.
AudioTranscriptionOptions setLanguage(String language)

Set the language property: The primary spoken language of the audio data to be transcribed, supplied as a two-letter ISO-639-1 language code such as 'en' or 'fr'.
AudioTranscriptionOptions setModel(String model)

Set the model property: The model to use for this transcription request.
AudioTranscriptionOptions setPrompt(String prompt)

Set the prompt property: An optional hint to guide the model's style or continue from a prior audio segment.
AudioTranscriptionOptions setResponseFormat(AudioTranscriptionFormat responseFormat)

Set the responseFormat property: The requested format of the transcription response data, which will influence the content and detail of the result.
AudioTranscriptionOptions setTemperature(Double temperature)

Set the temperature property: The sampling temperature, between 0 and 1.
AudioTranscriptionOptions setTimestampGranularities(List<AudioTranscriptionTimestampGranularity> timestampGranularities)

Set the timestampGranularities property: The timestamp granularities to populate for this transcription.

Methods inherited from java.lang.Object

clone equals finalize getClass hashCode notify notifyAll toString wait wait wait

Constructor Details

AudioTranscriptionOptions

public AudioTranscriptionOptions(byte[] file)

Creates an instance of AudioTranscriptionOptions class.

Parameters:

file - the file value to set.

Method Details

getFile

public byte[] getFile()

Get the file property: The audio data to transcribe. This must be the binary content of a file in one of the supported media formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.

Returns:

the file value.

getFilename

public String getFilename()

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

Returns:

the filename value.

getLanguage

public String getLanguage()

Get the language property: The primary spoken language of the audio data to be transcribed, supplied as a two-letter ISO-639-1 language code such as 'en' or 'fr'. Providing this known input language is optional but may improve the accuracy and/or latency of transcription.

Returns:

the language value.

getModel

public String getModel()

Get the model property: The model to use for this transcription request.

Returns:

the model value.

getPrompt

public String getPrompt()

Get the prompt property: 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 value.

getResponseFormat

public AudioTranscriptionFormat getResponseFormat()

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

Returns:

the responseFormat value.

getTemperature

public Double getTemperature()

Get the temperature property: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

Returns:

the temperature value.

getTimestampGranularities

public List getTimestampGranularities()

Get the timestampGranularities property: The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.

Returns:

the timestampGranularities value.

setFilename

public AudioTranscriptionOptions setFilename(String filename)

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

Parameters:

filename - the filename value to set.

Returns:

the AudioTranscriptionOptions object itself.

setLanguage

public AudioTranscriptionOptions setLanguage(String language)

Set the language property: The primary spoken language of the audio data to be transcribed, supplied as a two-letter ISO-639-1 language code such as 'en' or 'fr'. Providing this known input language is optional but may improve the accuracy and/or latency of transcription.

Parameters:

language - the language value to set.

Returns:

the AudioTranscriptionOptions object itself.

setModel

public AudioTranscriptionOptions setModel(String model)

Set the model property: The model to use for this transcription request.

Parameters:

model - the model value to set.

Returns:

the AudioTranscriptionOptions object itself.

setPrompt

public AudioTranscriptionOptions setPrompt(String prompt)

Set the prompt property: 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 value to set.

Returns:

the AudioTranscriptionOptions object itself.

setResponseFormat

public AudioTranscriptionOptions setResponseFormat(AudioTranscriptionFormat responseFormat)

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

Parameters:

responseFormat - the responseFormat value to set.

Returns:

the AudioTranscriptionOptions object itself.

setTemperature

public AudioTranscriptionOptions setTemperature(Double temperature)

Set the temperature property: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

Parameters:

temperature - the temperature value to set.

Returns:

the AudioTranscriptionOptions object itself.

setTimestampGranularities

public AudioTranscriptionOptions setTimestampGranularities(List timestampGranularities)

Set the timestampGranularities property: The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.

Parameters:

timestampGranularities - the timestampGranularities value to set.

Returns:

the AudioTranscriptionOptions object itself.

Applies to