Class OpenAiTextToSpeechModel

java.lang.Object

dev.langchain4j.model.openai.OpenAiTextToSpeechModel

All Implemented Interfaces:

TextToSpeechModel

@Experimental
public class OpenAiTextToSpeechModel
extends Object
implements TextToSpeechModel

Represents an OpenAI text-to-speech model with a speech generation interface. The supported models are tts-1, tts-1-hd, gpt-4o-mini-tts, and gpt-4o-mini-tts-2025-12-15.
You can find a description of the parameters here.

Since:

1.18.0

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	OpenAiTextToSpeechModel.Builder

Constructor Summary

Constructors

Constructor	Description
OpenAiTextToSpeechModel(OpenAiTextToSpeechModel.Builder builder)

Method Summary

Modifier and Type	Method	Description
static OpenAiTextToSpeechModel.Builder	builder()
ModelProvider	provider()
TextToSpeechResponse	synthesize(TextToSpeechRequest audioRequest)	Given a text-to-speech request, synthesizes speech audio.

Methods inherited from class Object

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

Methods inherited from interface TextToSpeechModel

synthesize

Constructor Details

OpenAiTextToSpeechModel

public OpenAiTextToSpeechModel(OpenAiTextToSpeechModel.Builder builder)

Method Details

synthesize

public TextToSpeechResponse synthesize(TextToSpeechRequest audioRequest)

Description copied from interface: TextToSpeechModel

Given a text-to-speech request, synthesizes speech audio.

Specified by:

synthesize in interface TextToSpeechModel

Parameters:

audioRequest - The speech request containing the input text and optional parameters.

Returns:

The generated speech response.

provider

public ModelProvider provider()

Specified by:

provider in interface TextToSpeechModel

builder

public static OpenAiTextToSpeechModel.Builder builder()