com.alibaba.dashscope.audio.http_tts

类 HttpSpeechSynthesizer

java.lang.Object

com.alibaba.dashscope.audio.http_tts.HttpSpeechSynthesizer

public class HttpSpeechSynthesizer
extends Object

HTTP-based Speech Synthesizer using Server-Sent Events (SSE). This class provides a simple interface for text-to-speech synthesis via HTTP SSE protocol.

Supports models like CosyVoice (cosyvoice-v3-flash, etc.) that use HTTP SSE for streaming synthesis.

作者:

songsong.sss

构造器概要

构造器

构造器和说明
HttpSpeechSynthesizer() Creates a new HttpSpeechSynthesizer instance with default settings.

方法概要

限定符和类型	方法和说明
HttpSpeechSynthesisResult	call(HttpSpeechSynthesisParam param) Synchronous call without SSE - returns a result containing the audio URL.
ByteBuffer	callAndReturnAudio(HttpSpeechSynthesisParam param) Streaming call that returns audio data as a ByteBuffer.
void	streamCall(HttpSpeechSynthesisParam param, ResultCallback<HttpSpeechSynthesisResult> callback) Streaming call with callback interface.

从类继承的方法 java.lang.Object

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

构造器详细资料

HttpSpeechSynthesizer

public HttpSpeechSynthesizer()

Creates a new HttpSpeechSynthesizer instance with default settings.

方法详细资料

call

public HttpSpeechSynthesisResult call(HttpSpeechSynthesisParam param)
                               throws ApiException,
                                      NoApiKeyException,
                                      InputRequiredException

Synchronous call without SSE - returns a result containing the audio URL. This is a simpler, faster call that returns a download URL instead of streaming audio data.

Use this method when you want to get the audio URL and download it later.

Example response:

 {
   "request_id": "xxx",
   "output": {
     "finish_reason": "stop",
     "audio": {
       "url": "http://dashscope-result-bj.oss-cn-beijing.aliyuncs.com/...",
       "id": "audio_xxx",
       "expires_at": 1772697707
     }
   },
   "usage": { "characters": 15 }
 }
 

参数:

param - The synthesis parameters

返回:

HttpSpeechSynthesisResult containing audio URL and metadata

抛出:

ApiException - If the API call fails

NoApiKeyException - If the API key is not configured

InputRequiredException - If required parameters are missing

streamCall

public void streamCall(HttpSpeechSynthesisParam param,
                       ResultCallback<HttpSpeechSynthesisResult> callback)
                throws ApiException,
                       NoApiKeyException,
                       InputRequiredException

Streaming call with callback interface. Results are delivered through the callback as they arrive.

参数:

param - The synthesis parameters

callback - The callback to receive synthesis results

抛出:

ApiException - If the API call fails

NoApiKeyException - If the API key is not configured

InputRequiredException - If required parameters are missing

callAndReturnAudio

public ByteBuffer callAndReturnAudio(HttpSpeechSynthesisParam param)
                              throws ApiException,
                                     NoApiKeyException,
                                     InputRequiredException

Streaming call that returns audio data as a ByteBuffer. This method blocks until the audio data is fully received.

参数:

param - The synthesis parameters

返回:

The accumulated audio data as ByteBuffer

抛出:

ApiException - If the API call fails

NoApiKeyException - If the API key is not configured

InputRequiredException - If required parameters are missing