Package org.springframework.ai.openai

Class OpenAiAudioTranscriptionModel

java.lang.Object

org.springframework.ai.openai.OpenAiAudioTranscriptionModel

All Implemented Interfaces:

TranscriptionModel, Model<AudioTranscriptionPrompt,AudioTranscriptionResponse>

public final class OpenAiAudioTranscriptionModel
extends Object
implements TranscriptionModel

OpenAI audio transcription model implementation using the OpenAI Java SDK. You provide as input the audio file you want to transcribe and the desired output file format of the transcription of the audio.

Author:

Michael Lavelle, Christian Tzolov, Thomas Vitale, Ilayaperumal Gopinathan

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final class	OpenAiAudioTranscriptionModel.Builder	Builder for creating OpenAiAudioTranscriptionModel instances.

Method Summary

Modifier and Type	Method	Description
static OpenAiAudioTranscriptionModel.Builder	builder()	Creates a new builder for OpenAiAudioTranscriptionModel.
AudioTranscriptionResponse	call(AudioTranscriptionPrompt transcriptionPrompt)	Transcribes the audio from the given prompt.
OpenAiAudioTranscriptionOptions	getOptions()	Gets the transcription options for this model.
OpenAiAudioTranscriptionModel.Builder	mutate()	Creates a builder initialized with this model's configuration.

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.springframework.ai.audio.transcription.TranscriptionModel

transcribe, transcribe

Method Details

builder

public static OpenAiAudioTranscriptionModel.Builder builder()

Creates a new builder for OpenAiAudioTranscriptionModel.

Returns:

a new builder instance

mutate

public OpenAiAudioTranscriptionModel.Builder mutate()

Creates a builder initialized with this model's configuration.

Returns:

a builder for creating a modified copy

getOptions

public OpenAiAudioTranscriptionOptions getOptions()

Gets the transcription options for this model.

Returns:

the transcription options

call

public AudioTranscriptionResponse call(AudioTranscriptionPrompt transcriptionPrompt)

Description copied from interface: TranscriptionModel

Transcribes the audio from the given prompt.

Specified by:

call in interface Model<AudioTranscriptionPrompt,AudioTranscriptionResponse>

Specified by:

call in interface TranscriptionModel

Parameters:

transcriptionPrompt - The prompt containing the audio resource and options.

Returns:

The transcription response.