Java SDK 2.0 - 语音合成| 阿里云

提示:

在使用SDK之前，请先确保已阅读了接口说明文档。

下载安装

可从maven 服务器下载最新版本SDK：

<dependency>
    <groupId>com.alibaba.nls</groupId>
    <artifactId>nls-sdk-tts</artifactId>
    <version>2.1.0</version>
</dependency>

使用方式参见下面代码示例。Demo 源码下载链接。

demo 解压后，在pom 目录运行mvn package ，会在target目录生成可执行jarnls-example-tts-2.0.0-jar-with-dependencies.jar将此jar拷贝到目标服务器，可用于快速验证及压测服务。

服务验证

java -cp nls-example-tts-2.0.0-jar-with-dependencies.jar com.alibaba.nls.client.SpeechSynthesizerDemo并按提示提供相应参数，运行后在命令执行目录生成logs/nls.log

服务压测

java -jar nls-example-tts-2.0.0-jar-with-dependencies.jar并按提示提供相应参数，其中阿里云服务url参数为： wss://nls-gateway-ap-southeast-1.aliyuncs.com/ws/v1 ，并发数根据用户已购买并发谨慎选择。

温馨提示：自行压测超过2并发会产生费用。

关键接口

NlsClient：语音处理client，相当于所有语音相关处理类的factory，全局创建一个实例即可。线程安全。
SpeechSynthesizer：语音合成处理类，设置请求参数，发送请求。非线程安全。

SpeechSynthesizerListener：语音合成监听类，监听返回结果。非线程安全。有如下两个抽象方法需要实现：

  /**
   * 接收语音合成二进制数据
   */
  abstract public void onMessage(ByteBuffer message);
  /**
   * 语音合成结束事件通知
   *
   * @param response
   */
  abstract public void onComplete(SpeechSynthesizerResponse response);

更多介绍参见API文档链接: Java API接口说明

SDK 调用注意事项

NlsClient对象创建一次可以重复使用，每次创建消耗性能。NlsClient使用了netty的框架，创建时比较消耗时间和资源，但创建之后可以重复利用。建议调用程序将NlsClient的创建和关闭与程序本身的生命周期结合。
SpeechSynthesizer对象不能重复使用，一个语音合成任务对应一个SpeechSynthesizer对象。例如有N个文本需要语音合成，则要进行N次语音合成任务，创建N个SpeechSynthesizer对象。
实现的SpeechSynthesizerListener对象和SpeechSynthesizer对象是一一对应的，不能将一个SpeechSynthesizerListener对象设置到多个SpeechSynthesizer对象中，否则不能区分是哪个语音合成任务。
Java SDK依赖了Netty网络库，版本需设置为4.1.17.Final及以上。如果您的应用中依赖了Netty，请确保版本符合要求。

代码示例

说明1：Demo显示了如何在在创建NlsClient对象的时候设置URL:

client = new NlsClient("ws://nls-gateway-ap-southeast-1.aliyuncs.com/ws/v1", accessToken);

说明2：Demo中将合成的音频保存在了文件中，如果您需要播放音频且对实时性要求较高，建议使用流式播放，即边接收语音数据边播放，减少延时。

示例：

package com.alibaba.nls.client;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.nio.ByteBuffer;
import com.alibaba.nls.client.protocol.NlsClient;
import com.alibaba.nls.client.protocol.OutputFormatEnum;
import com.alibaba.nls.client.protocol.SampleRateEnum;
import com.alibaba.nls.client.protocol.tts.SpeechSynthesizer;
import com.alibaba.nls.client.protocol.tts.SpeechSynthesizerListener;
import com.alibaba.nls.client.protocol.tts.SpeechSynthesizerResponse;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
 * The demo of speech synthesis.
 * (for demo show only)
 */
public class SpeechSynthesizerDemo {
    private static final Logger logger = LoggerFactory.getLogger(SpeechSynthesizerDemo.class);
    private static long startTime;
    private String appKey;
    NlsClient client;
    public SpeechSynthesizerDemo(String appKey, String token) {
        this.appKey = appKey;
        // Create an NlsClient object. You can globally create an NlsClient object and specify the endpoint.
        client = new NlsClient("wss://nls-gateway-ap-southeast-1.aliyuncs.com/ws/v1", token);
    }
    private static SpeechSynthesizerListener getSynthesizerListener() {
        SpeechSynthesizerListener listener = null;
        try {
            listener = new SpeechSynthesizerListener() {
                File f=new File("tts_test.wav");
                FileOutputStream fout = new FileOutputStream(f);
                private boolean firstRecvBinary = true;
                // Speech synthesis is completed.
                @Override
                public void onComplete(SpeechSynthesizerResponse response) {
                    System.out.println("name: " + response.getName() + ", status: " + response.getStatus()+", output file :"+f.getAbsolutePath());
                }
                // The speech binary data of speech synthesis.
                @Override
                public void onMessage(ByteBuffer message) {
                    try {
                        if(firstRecvBinary) {
                            // the latency of first binary
                            firstRecvBinary = false;
                            long now = System.currentTimeMillis();
                            logger.info("tts first latency : " + (now - SpeechSynthesizerDemo.startTime) + " ms");
                        }
                        byte[] bytesArray = new byte[message.remaining()];
                        message.get(bytesArray, 0, bytesArray.length);
                        //System.out.println("write array:" + bytesArray.length);
                        fout.write(bytesArray);
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
                @Override
                public void onFail(SpeechSynthesizerResponse response){
                    System.out.println(
                        "task_id: " + response.getTaskId() +
                            // the code 20000000 indicates that the request is successful.
                            ", status: " + response.getStatus() +
                            // error message
                            ", status_text: " + response.getStatusText());
                }
            };
        } catch (Exception e) {
            e.printStackTrace();
        }
        return listener;
    }
    public void process() {
        SpeechSynthesizer synthesizer = null;
        try {
            //Create an object and establish a connection.
            synthesizer = new SpeechSynthesizer(client, getSynthesizerListener());
            synthesizer.setAppKey(appKey);
            //Specify the audio coding format of the returned audio file.
            synthesizer.setFormat(OutputFormatEnum.WAV);
            //Specify the audio sampling rate of the returned audio file.
            synthesizer.setSampleRate(SampleRateEnum.SAMPLE_RATE_16K);
            //The speaker.
            synthesizer.setVoice("siyue");
            //Optional. The intonation. Value range: -500 to 500. Default value: 0.
            synthesizer.setPitchRate(100);
            //The speed. Value range: -500 to 500. Default value: 0.
            synthesizer.setSpeechRate(100);
            //Set the text to be synthesized.
            synthesizer.setText("hello world!");
            //Serialize preceding parameters to the JSON format and send them to the server for confirmation.
            long start = System.currentTimeMillis();
            synthesizer.start();
            logger.info("tts start latency " + (System.currentTimeMillis() - start) + " ms");
            SpeechSynthesizerDemo.startTime = System.currentTimeMillis();
            //Wait until the speech synthesis is completed.
            synthesizer.waitForComplete();
            logger.info("tts stop latency " + (System.currentTimeMillis() - start) + " ms");
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            //关闭连接
            if (null != synthesizer) {
                synthesizer.close();
            }
        }
    }
    public void shutdown() {
        client.shutdown();
    }
    public static void main(String[] args) throws Exception {
        String appKey = "your appkey";
        String token  = "your token";
        if (args.length == 2) {
            appKey   = args[0];
            token    = args[1];
        } else {
            System.err.println("run error, need params: " + "<app-key> <token>");
            System.exit(-1);
        }
        SpeechSynthesizerDemo demo = new SpeechSynthesizerDemo(appKey, token);
        demo.process();
        demo.shutdown();
    }
}