全部产品
Search

搜索本产品

    Java SDK 2.0

    文档中心
    下载PDF

    Java SDK 2.0

    更新时间： 2020-11-03

    提示:

    下载安装

    可从maven 服务器下载最新版本SDK：

    1. <dependency>
    2.     <groupId>com.alibaba.nls</groupId>
    3.     <artifactId>nls-sdk-tts</artifactId>
    4.     <version>2.1.0</version>
    5. </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：
      1.   /**
      2.    * 接收语音合成二进制数据
      3.    */
      4.   abstract public void onMessage(ByteBuffer message);
      5.   /**
      6.    * 语音合成结束事件通知
      7.    *
      8.    * @param response
      9.    */
      10.   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

    1. 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。
    2. 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。
    3. 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。
    4. 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:

    1. 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：

    1. package com.alibaba.nls.client;
    3. import java.io.File;
    4. import java.io.FileOutputStream;
    5. import java.io.IOException;
    6. import java.nio.ByteBuffer;
    8. import com.alibaba.nls.client.protocol.NlsClient;
    9. import com.alibaba.nls.client.protocol.OutputFormatEnum;
    10. import com.alibaba.nls.client.protocol.SampleRateEnum;
    11. import com.alibaba.nls.client.protocol.tts.SpeechSynthesizer;
    12. import com.alibaba.nls.client.protocol.tts.SpeechSynthesizerListener;
    13. import com.alibaba.nls.client.protocol.tts.SpeechSynthesizerResponse;
    15. import org.slf4j.Logger;
    16. import org.slf4j.LoggerFactory;
    18. /**
    19.  * The demo of speech synthesis.
    20.  * (for demo show only)
    21.  */
    22. public class SpeechSynthesizerDemo {
    23.     private static final Logger logger = LoggerFactory.getLogger(SpeechSynthesizerDemo.class);
    24.     private static long startTime;
    25.     private String appKey;
    26.     NlsClient client;
    28.     public SpeechSynthesizerDemo(String appKey, String token) {
    29.         this.appKey = appKey;
    30.         // Create an NlsClient object. You can globally create an NlsClient object and specify the endpoint.
    31.         client = new NlsClient("wss://nls-gateway-ap-southeast-1.aliyuncs.com/ws/v1", token);
    32.     }
    34.     private static SpeechSynthesizerListener getSynthesizerListener() {
    35.         SpeechSynthesizerListener listener = null;
    36.         try {
    37.             listener = new SpeechSynthesizerListener() {
    38.                 File f=new File("tts_test.wav");
    39.                 FileOutputStream fout = new FileOutputStream(f);
    40.                 private boolean firstRecvBinary = true;
    42.                 // Speech synthesis is completed.
    43.                 @Override
    44.                 public void onComplete(SpeechSynthesizerResponse response) {
    45.                     System.out.println("name: " + response.getName() + ", status: " + response.getStatus()+", output file :"+f.getAbsolutePath());
    46.                 }
    48.                 // The speech binary data of speech synthesis.
    49.                 @Override
    50.                 public void onMessage(ByteBuffer message) {
    51.                     try {
    52.                         if(firstRecvBinary) {
    53.                             // the latency of first binary
    54.                             firstRecvBinary = false;
    55.                             long now = System.currentTimeMillis();
    56.                             logger.info("tts first latency : " + (now - SpeechSynthesizerDemo.startTime) + " ms");
    57.                         }
    58.                         byte[] bytesArray = new byte[message.remaining()];
    59.                         message.get(bytesArray, 0, bytesArray.length);
    60.                         //System.out.println("write array:" + bytesArray.length);
    61.                         fout.write(bytesArray);
    62.                     } catch (IOException e) {
    63.                         e.printStackTrace();
    64.                     }
    65.                 }
    66.                 @Override
    67.                 public void onFail(SpeechSynthesizerResponse response){
    68.                     System.out.println(
    69.                         "task_id: " + response.getTaskId() +
    70.                             // the code 20000000 indicates that the request is successful.
    71.                             ", status: " + response.getStatus() +
    72.                             // error message
    73.                             ", status_text: " + response.getStatusText());
    74.                 }
    75.             };
    76.         } catch (Exception e) {
    77.             e.printStackTrace();
    78.         }
    79.         return listener;
    80.     }
    82.     public void process() {
    83.         SpeechSynthesizer synthesizer = null;
    84.         try {
    85.             //Create an object and establish a connection.
    86.             synthesizer = new SpeechSynthesizer(client, getSynthesizerListener());
    87.             synthesizer.setAppKey(appKey);
    88.             //Specify the audio coding format of the returned audio file.
    89.             synthesizer.setFormat(OutputFormatEnum.WAV);
    90.             //Specify the audio sampling rate of the returned audio file.
    91.             synthesizer.setSampleRate(SampleRateEnum.SAMPLE_RATE_16K);
    92.             //The speaker.
    93.             synthesizer.setVoice("siyue");
    94.             //Optional. The intonation. Value range: -500 to 500. Default value: 0.
    95.             synthesizer.setPitchRate(100);
    96.             //The speed. Value range: -500 to 500. Default value: 0.
    97.             synthesizer.setSpeechRate(100);
    98.             //Set the text to be synthesized.
    99.             synthesizer.setText("hello world!");
    101.             //Serialize preceding parameters to the JSON format and send them to the server for confirmation.
    102.             long start = System.currentTimeMillis();
    103.             synthesizer.start();
    104.             logger.info("tts start latency " + (System.currentTimeMillis() - start) + " ms");
    106.             SpeechSynthesizerDemo.startTime = System.currentTimeMillis();
    108.             //Wait until the speech synthesis is completed.
    109.             synthesizer.waitForComplete();
    110.             logger.info("tts stop latency " + (System.currentTimeMillis() - start) + " ms");
    111.         } catch (Exception e) {
    112.             e.printStackTrace();
    113.         } finally {
    114.             //关闭连接
    115.             if (null != synthesizer) {
    116.                 synthesizer.close();
    117.             }
    118.         }
    119.     }
    121.     public void shutdown() {
    122.         client.shutdown();
    123.     }
    125.     public static void main(String[] args) throws Exception {
    126.         String appKey = "your appkey";
    127.         String token  = "your token";
    128.         if (args.length == 2) {
    129.             appKey   = args[0];
    130.             token    = args[1];
    131.         } else {
    132.             System.err.println("run error, need params: " + "<app-key> <token>");
    133.             System.exit(-1);
    134.         }
    136.         SpeechSynthesizerDemo demo = new SpeechSynthesizerDemo(appKey, token);
    137.         demo.process();
    138.         demo.shutdown();
    139.     }
    140. }
    免费试用 免费试用