Package com.alibaba.cloud.ai.dashscope.audio

Class DashScopeAudioSpeechModel

java.lang.Object

com.alibaba.cloud.ai.dashscope.audio.DashScopeAudioSpeechModel

All Implemented Interfaces:

org.springframework.ai.audio.tts.StreamingTextToSpeechModel, org.springframework.ai.audio.tts.TextToSpeechModel, org.springframework.ai.model.Model<org.springframework.ai.audio.tts.TextToSpeechPrompt,org.springframework.ai.audio.tts.TextToSpeechResponse>, org.springframework.ai.model.StreamingModel<org.springframework.ai.audio.tts.TextToSpeechPrompt,org.springframework.ai.audio.tts.TextToSpeechResponse>

public class DashScopeAudioSpeechModel
extends Object
implements org.springframework.ai.audio.tts.TextToSpeechModel

Audio Speech: input text, output audio.

Author:

kevinlin09, xuguan

Constructor Summary

Constructors

Constructor	Description
DashScopeAudioSpeechModel(DashScopeAudioSpeechApi audioSpeechApi)
DashScopeAudioSpeechModel(DashScopeAudioSpeechApi audioSpeechApi, DashScopeAudioSpeechOptions defaultOptions)
DashScopeAudioSpeechModel(DashScopeAudioSpeechApi audioSpeechApi, DashScopeAudioSpeechOptions defaultOptions, org.springframework.retry.support.RetryTemplate retryTemplate)

Method Summary

Modifier and Type	Method	Description
org.springframework.ai.audio.tts.TextToSpeechResponse	call(org.springframework.ai.audio.tts.TextToSpeechPrompt prompt)
DashScopeAudioSpeechApi.Request	createRequest(org.springframework.ai.audio.tts.TextToSpeechPrompt prompt, String taskId, DashScopeWebSocketClient.EventType action)
reactor.core.publisher.Flux<org.springframework.ai.audio.tts.TextToSpeechResponse>	stream(org.springframework.ai.audio.tts.TextToSpeechPrompt prompt)

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.tts.StreamingTextToSpeechModel

stream, stream

Methods inherited from interface org.springframework.ai.audio.tts.TextToSpeechModel

call, getDefaultOptions

Constructor Details

DashScopeAudioSpeechModel

public DashScopeAudioSpeechModel(DashScopeAudioSpeechApi audioSpeechApi)

DashScopeAudioSpeechModel

public DashScopeAudioSpeechModel(DashScopeAudioSpeechApi audioSpeechApi,
 DashScopeAudioSpeechOptions defaultOptions)

DashScopeAudioSpeechModel

public DashScopeAudioSpeechModel(DashScopeAudioSpeechApi audioSpeechApi,
 DashScopeAudioSpeechOptions defaultOptions,
 org.springframework.retry.support.RetryTemplate retryTemplate)

Method Details

call

public org.springframework.ai.audio.tts.TextToSpeechResponse call(org.springframework.ai.audio.tts.TextToSpeechPrompt prompt)

Specified by:

call in interface org.springframework.ai.model.Model<org.springframework.ai.audio.tts.TextToSpeechPrompt,org.springframework.ai.audio.tts.TextToSpeechResponse>

Specified by:

call in interface org.springframework.ai.audio.tts.TextToSpeechModel

stream

public reactor.core.publisher.Flux<org.springframework.ai.audio.tts.TextToSpeechResponse> stream(org.springframework.ai.audio.tts.TextToSpeechPrompt prompt)

Specified by:

stream in interface org.springframework.ai.model.StreamingModel<org.springframework.ai.audio.tts.TextToSpeechPrompt,org.springframework.ai.audio.tts.TextToSpeechResponse>

Specified by:

stream in interface org.springframework.ai.audio.tts.StreamingTextToSpeechModel

createRequest

public DashScopeAudioSpeechApi.Request createRequest(org.springframework.ai.audio.tts.TextToSpeechPrompt prompt,
 String taskId,
 DashScopeWebSocketClient.EventType action)