Package org.springframework.ai.openai.api

Class OpenAiAudioApi

java.lang.Object

org.springframework.ai.openai.api.OpenAiAudioApi

public class OpenAiAudioApi
extends Object

Turn audio into text or text into audio. Based on OpenAI Audio

Since:

0.8.1

Author:

Christian Tzolov

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final record	OpenAiAudioApi.SpeechRequest	Request to generates audio from the input text.
static final record	OpenAiAudioApi.StructuredResponse	The Transcription Object represents a verbose json transcription response returned by model, based on the provided input.
static final record	OpenAiAudioApi.TranscriptionRequest	Request to transcribe an audio file to text.
static enum	OpenAiAudioApi.TranscriptResponseFormat	The format of the transcript and translation outputs, in one of these options: json, text, srt, verbose_json, or vtt.
static final record	OpenAiAudioApi.TranslationRequest	Request to translate an audio file to English.
static enum	OpenAiAudioApi.TtsModel	TTS is an AI model that converts text to natural sounding spoken text.
static enum	OpenAiAudioApi.WhisperModel	Whisper is a general-purpose speech recognition model.

Constructor Summary

Constructors

Constructor	Description
OpenAiAudioApi(String openAiToken)	Create a new audio api.
OpenAiAudioApi(String baseUrl, String apiKey, org.springframework.util.MultiValueMap<String,String> headers, org.springframework.web.client.RestClient.Builder restClientBuilder, org.springframework.web.reactive.function.client.WebClient.Builder webClientBuilder, org.springframework.web.client.ResponseErrorHandler responseErrorHandler)	Create a new audio api.
OpenAiAudioApi(String baseUrl, String openAiToken, org.springframework.web.client.RestClient.Builder restClientBuilder, org.springframework.web.client.ResponseErrorHandler responseErrorHandler)	Create a new audio api.
OpenAiAudioApi(String baseUrl, String apiKey, org.springframework.web.client.RestClient.Builder restClientBuilder, org.springframework.web.reactive.function.client.WebClient.Builder webClientBuilder, org.springframework.web.client.ResponseErrorHandler responseErrorHandler)	Create a new audio api.

Method Summary

Modifier and Type	Method	Description
org.springframework.http.ResponseEntity<byte[]>	createSpeech(OpenAiAudioApi.SpeechRequest requestBody)	Request to generates audio from the input text.
org.springframework.http.ResponseEntity<?>	createTranscription(OpenAiAudioApi.TranscriptionRequest requestBody)	Transcribes audio into the input language.
<T> org.springframework.http.ResponseEntity<T>	createTranscription(OpenAiAudioApi.TranscriptionRequest requestBody, Class<T> responseType)	Transcribes audio into the input language.
org.springframework.http.ResponseEntity<?>	createTranslation(OpenAiAudioApi.TranslationRequest requestBody)	Translates audio into English.
<T> org.springframework.http.ResponseEntity<T>	createTranslation(OpenAiAudioApi.TranslationRequest requestBody, Class<T> responseType)	Translates audio into English.
reactor.core.publisher.Flux<org.springframework.http.ResponseEntity<byte[]>>	stream(OpenAiAudioApi.SpeechRequest requestBody)	Streams audio generated from the input text.

Methods inherited from class java.lang.Object

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

Constructor Details

OpenAiAudioApi

public OpenAiAudioApi(String openAiToken)

Create a new audio api.

Parameters:

openAiToken - OpenAI apiKey.

OpenAiAudioApi

public OpenAiAudioApi(String baseUrl,
 String openAiToken,
 org.springframework.web.client.RestClient.Builder restClientBuilder,
 org.springframework.web.client.ResponseErrorHandler responseErrorHandler)

Create a new audio api.

Parameters:

baseUrl - api base URL.

openAiToken - OpenAI apiKey.

restClientBuilder - RestClient builder.

responseErrorHandler - Response error handler.

OpenAiAudioApi

public OpenAiAudioApi(String baseUrl,
 String apiKey,
 org.springframework.web.client.RestClient.Builder restClientBuilder,
 org.springframework.web.reactive.function.client.WebClient.Builder webClientBuilder,
 org.springframework.web.client.ResponseErrorHandler responseErrorHandler)

Create a new audio api.

Parameters:

baseUrl - api base URL.

apiKey - OpenAI apiKey.

restClientBuilder - RestClient builder.

webClientBuilder - WebClient builder.

responseErrorHandler - Response error handler.

OpenAiAudioApi

public OpenAiAudioApi(String baseUrl,
 String apiKey,
 org.springframework.util.MultiValueMap<String,String> headers,
 org.springframework.web.client.RestClient.Builder restClientBuilder,
 org.springframework.web.reactive.function.client.WebClient.Builder webClientBuilder,
 org.springframework.web.client.ResponseErrorHandler responseErrorHandler)

Create a new audio api.

Parameters:

baseUrl - api base URL.

apiKey - OpenAI apiKey.

headers - the http headers to use.

restClientBuilder - RestClient builder.

webClientBuilder - WebClient builder.

responseErrorHandler - Response error handler.

Method Details

createSpeech

public org.springframework.http.ResponseEntity<byte[]> createSpeech(OpenAiAudioApi.SpeechRequest requestBody)

Request to generates audio from the input text.

Parameters:

requestBody - The request body.

Returns:

Response entity containing the audio binary.

stream

public reactor.core.publisher.Flux<org.springframework.http.ResponseEntity<byte[]>> stream(OpenAiAudioApi.SpeechRequest requestBody)

Streams audio generated from the input text. This method sends a POST request to the OpenAI API to generate audio from the provided text. The audio is streamed back as a Flux of ResponseEntity objects, each containing a byte array of the audio data.

Parameters:

requestBody - The request body containing the details for the audio generation, such as the input text, model, voice, and response format.

Returns:

A Flux of ResponseEntity objects, each containing a byte array of the audio data.

createTranscription

public org.springframework.http.ResponseEntity<?> createTranscription(OpenAiAudioApi.TranscriptionRequest requestBody)

Transcribes audio into the input language.

Parameters:

requestBody - The request body.

Returns:

Response entity containing the transcribed text in either json or text format.

createTranscription

public <T>
org.springframework.http.ResponseEntity<T> createTranscription(OpenAiAudioApi.TranscriptionRequest requestBody,
 Class<T> responseType)

Transcribes audio into the input language. The response type is specified by the responseType parameter.

Type Parameters:

T - The response type.

Parameters:

requestBody - The request body.

responseType - The response type class.

Returns:

Response entity containing the transcribed text in the responseType format.

createTranslation

public org.springframework.http.ResponseEntity<?> createTranslation(OpenAiAudioApi.TranslationRequest requestBody)

Translates audio into English.

Parameters:

requestBody - The request body.

Returns:

Response entity containing the transcribed text in either json or text format.

createTranslation

public <T>
org.springframework.http.ResponseEntity<T> createTranslation(OpenAiAudioApi.TranslationRequest requestBody,
 Class<T> responseType)

Translates audio into English. The response type is specified by the responseType parameter.

Type Parameters:

T - The response type.

Parameters:

requestBody - The request body.

responseType - The response type class.

Returns:

Response entity containing the transcribed text in the responseType format.