手把手教你用JAVA调用Websocket实现“声音转换”功能（变声）标贝科技
前言
什么是声音转换？
基于深度学习和迁移学习技术，精准将原说话人的声音转换为目标说话人，同时保留原说话人的风格特色。让声音有更多的表现形式。
一、内容太长不愿意看，直接使用系列
首先确认接口调用要求：
实现方式：Websocket
支持音频文件的编码格式及文件名的后缀: pcm
支持音频文件的采样率/位深: 16000Hz/16bit
支持的语言:中文普通话
音频有效时长：不超过180分钟
确认无误后，直接执行 2.2获取权限+2.3.5完整代码示例
二、用JAVA调用标贝科技“声音转换”接口使用流程
2.1.环境准备
java
2.2.获取权限
2.1.1.登录
地址：标贝科技智能语音开放平台
点击上方地址登录，支持短信、密码、微信三种登录方式。
2.1.2.创建应用
登录后，点击创建应用，填写相关信息(未实名认证只能创建一个应用)
（注：实名认证后可获得创建多个应用的权限）
进入应用，其中包含的技术产品有：语音识别、语音合成、声音复刻、声音转换
页面中功能主要包括：服务用量管理、购买服务量管理、开发者文档、授权管理、套餐管理
2.1.3.获取token
点击声音转换—>授权管理—>显示—>获取APISecret—>（获取访问令牌token）
2.3.代码实现
2.3.1.获取token
/*** 授权：需要在开放平台获取【https://ai.data-/#/?source=qaz123】*/private static final String clientId = "输入你的clientid";private static final String clientSecret = "输入你的clientsecret";/*** 获取token的地址信息*/public static String tokenUrl = "https://openapi.data-/oauth/2.0/token?grant_type=client_credentials&client_secret=%s&client_id=%s";public static String getAccessToken() {String accessToken = "";OkHttpClient client = new OkHttpClient();// request 默认是get请求String url = String.format(tokenUrl, clientSecret, clientId);Request request = new Request.Builder().url(url).build();JSONObject jsonObject;try {Response response = client.newCall(request).execute();if (response.isSuccessful()) {// 解析String resultJson = response.body().string();jsonObject = JSON.parseObject(resultJson);accessToken = jsonObject.getString("access_token");}} catch (Exception e) {e.printStackTrace();}return accessToken;}
2.3.2.配置获取音频文件路径和声音转换后的保存路径
/*** 文件路径【开发者需要根据实际路径调整。支持的音频编码格式:PCM,采样率16K,位深16bit,中文普通话,时长不超过180分钟】*/private static final String pcmFile = "";/*** 文件夹路径【声音转换后文件存放地址，开发者需要根据实际路径调整。】*/private static final String dic = "";
2.3.3.创建webscoket连接，配置接口参数
参数：
“access_token”：2.1.3中已获取
“voice_name”：代码中已提供（平台提供五种音色供你测试）
“enable_vad”：true代表启动服务端vad功能，默认false。如果启动系统会根据输入音频进行检测，过 滤环境噪音。否则直接将原始输入音频进行转换。
“align_input”：true代表输出音频与输入音频进行对齐,默认false。即开启vad时会保留静音部分，false丢弃静音部分。
“lastpkg”：是否为最后一包，当时发送最后一包数据时设置为true 告诉系统输入完成
@Overridepublic void onOpen(WebSocket webSocket, Response response) {super.onOpen(webSocket, response);this.startTime = timeBegin.get();// 该demo直接从文件中读取音频流【实际场景可能是实时从麦克风获取音频流，开发者自行修改获取音频流的逻辑即可】new Thread(() -> {File file = new File(pcmFile);// 连接成功，开始发送数据// 第二部分是一个JSON的字符串JSONObject jsonObject = new JSONObject();jsonObject.put("access_token", accessToken);jsonObject.put("voice_name", voiceName);jsonObject.put("enable_vad", true);jsonObject.put("align_input", true);jsonObject.put("lastpkg", false);int length = jsonObject.toJSONString().getBytes().length;// 第一部分byte[] b = new byte[4];b[0] = (byte) (length >> 24 & 0xFF);b[1] = (byte) (length >> 16 & 0xFF);b[2] = (byte) (length >> 8 & 0xFF);b[3] = (byte) (length & 0xFF);FileInputStream fileInputStream = null;ByteArrayOutputStream byteOut = null;try {fileInputStream = new FileInputStream(file);byteOut = new ByteArrayOutputStream();int size = 32000;byte[] byteArray = new byte[size];int totalLength = 0;int read = 0;// 发送音频while ((read = fileInputStream.read(byteArray, 0, size)) > 0) {totalLength += read;System.out.println();if (read == size && totalLength < file.length()) {byte[] bytes = ArrayUtils.addAll(ArrayUtils.addAll(b, jsonObject.toJSONString().getBytes()), byteArray);webSocket.send(new ByteString(bytes));Thread.sleep(40);} else {// 最后一包jsonObject.put("lastpkg", true);length = jsonObject.toJSONString().getBytes().length;b[0] = (byte) (length >> 24 & 0xFF);b[1] = (byte) (length >> 16 & 0xFF);b[2] = (byte) (length >> 8 & 0xFF);b[3] = (byte) (length & 0xFF);byte[] subarray = ArrayUtils.subarray(byteArray, 0, read);byte[] bytes = ArrayUtils.addAll(ArrayUtils.addAll(b, jsonObject.toJSONString().getBytes()), subarray);webSocket.send(new ByteString(bytes));}}System.out.println("all data is send");} catch (Exception e) {e.printStackTrace();} finally {if (fileInputStream != null) {try {fileInputStream.close();} catch (IOException e) {e.printStackTrace();}}if (byteOut != null) {try {byteOut.close();} catch (IOException e) {e.printStackTrace();}}}}).start();}
2.3.4.接收返回的语音流并写入文件
@Overridepublic void onMessage(WebSocket webSocket, ByteString bytes) {super.onMessage(webSocket, bytes);byte[] byteArray = bytes.toByteArray();// byte[]转lengthint length = (byteArray[0] << 24) + (byteArray[1] << 16) + (byteArray[2] << 8) + byteArray[3];byte[] jsonArray = ArrayUtils.subarray(byteArray, 4, 4 + length);String jsonStr = new String(jsonArray);JSONObject jsonObject = JSONObject.parseObject(jsonStr);byte[] subarray = ArrayUtils.subarray(byteArray, 4 + length, byteArray.length);File resultPcmFile = new File(dic, new File(pcmFile).getName().replace(".pcm", "_result.pcm"));if (!resultPcmFile.exists()) {try {resultPcmFile.createNewFile();} catch (IOException e) {e.printStackTrace();}}try {// 写入文件FileOutputStream outputStream = new FileOutputStream(resultPcmFile, true);IOUtils.write(subarray, outputStream);IOUtils.closeQuietly(outputStream);if ((int) jsonObject.get("errcode") == 0) {if (jsonObject.getBoolean("lastpkg")) {//说明数据全部返回完毕，可以关闭连接，释放资源System.out.println("session end ");System.out.println(sdf.format(startTime) + "开始");System.out.println(sdf.format(timeEnd.get()) + "结束");System.out.println("耗时:" + (timeEnd.get().getTime() - startTime.getTime()) + "ms");System.out.println("本次识别traceId ==》" + jsonObject.getString("traceid"));webSocket.close(1000, "");}} else {System.out.println("errCode=>" + jsonObject.getInteger("errcode") + " errMsg=>" + jsonObject.getString("errmsg") + " traceId=" + jsonObject.getString("traceid"));// 关闭连接webSocket.close(1000, "");System.out.println("发生错误，关闭连接");return;}} catch (Exception e) {e.printStackTrace();}}
2.3.5.完整代码示例
package ......import com.alibaba.fastjson.JSON;import com.alibaba.fastjson.JSONObject;import okhttp3.*;import okio.ByteString;import mons.io.IOUtils;import mons.lang3.ArrayUtils;import java.io.*;import java.text.SimpleDateFormat;import java.util.Date;/*** 声音转换WebSocket API接口调用示例* 附：声音转换Websocket API文档 【https://www.data-/specs/file/vc_api_websocket】* <p>* 注意：仅作为demo示例,失败重试、token过期重新获取、日志打印等优化工作需要开发者自行完成** @author data-baker*/public class VcWebSocketDemo extends WebSocketListener {/*** 授权：需要在开放平台获取【https://ai.data-/#/?source=qaz123】*/private static final String clientId = "输入你的clientid";private static final String clientSecret = "输入你的clientSecret";/*** 获取token的地址信息*/public static String tokenUrl = "https://openapi.data-/oauth/2.0/token?grant_type=client_credentials&client_secret=%s&client_id=%s";private static final String hostUrl = "wss://openapi.data-/ws/voice_conversion";/*** 文件路径【开发者需要根据实际路径调整。支持的音频编码格式:PCM,采样率16K,位深16bit,中文普通话,时长不超过180分钟】*/private static final String pcmFile = "";/*** 文件夹路径【声音转换后文件存放地址，开发者需要根据实际路径调整。】*/private static final String dic = "";private static final SimpleDateFormat sdf = new SimpleDateFormat("yyy-MM-dd HH:mm:ss.SSS");// 开始时间private static ThreadLocal<Date> timeBegin = ThreadLocal.withInitial(() -> new Date());// 结束时间private static ThreadLocal<Date> timeEnd = ThreadLocal.withInitial(() -> new Date());// 发音人private String voiceName = "Vc_baklong";private Date startTime;private String accessToken = getAccessToken();@Overridepublic void onOpen(WebSocket webSocket, Response response) {super.onOpen(webSocket, response);this.startTime = timeBegin.get();// 该demo直接从文件中读取音频流【实际场景可能是实时从麦克风获取音频流，开发者自行修改获取音频流的逻辑即可】new Thread(() -> {File file = new File(pcmFile);// 连接成功，开始发送数据// 第二部分是一个JSON的字符串JSONObject jsonObject = new JSONObject();jsonObject.put("access_token", accessToken);jsonObject.put("voice_name", voiceName);jsonObject.put("enable_vad", true);jsonObject.put("align_input", true);jsonObject.put("lastpkg", false);int length = jsonObject.toJSONString().getBytes().length;// 第一部分byte[] b = new byte[4];b[0] = (byte) (length >> 24 & 0xFF);b[1] = (byte) (length >> 16 & 0xFF);b[2] = (byte) (length >> 8 & 0xFF);b[3] = (byte) (length & 0xFF);FileInputStream fileInputStream = null;ByteArrayOutputStream byteOut = null;try {fileInputStream = new FileInputStream(file);byteOut = new ByteArrayOutputStream();int size = 32000;byte[] byteArray = new byte[size];int totalLength = 0;int read = 0;// 发送音频while ((read = fileInputStream.read(byteArray, 0, size)) > 0) {totalLength += read;System.out.println();if (read == size && totalLength < file.length()) {byte[] bytes = ArrayUtils.addAll(ArrayUtils.addAll(b, jsonObject.toJSONString().getBytes()), byteArray);webSocket.send(new ByteString(bytes));Thread.sleep(40);} else {// 最后一包jsonObject.put("lastpkg", true);length = jsonObject.toJSONString().getBytes().length;b[0] = (byte) (length >> 24 & 0xFF);b[1] = (byte) (length >> 16 & 0xFF);b[2] = (byte) (length >> 8 & 0xFF);b[3] = (byte) (length & 0xFF);byte[] subarray = ArrayUtils.subarray(byteArray, 0, read);byte[] bytes = ArrayUtils.addAll(ArrayUtils.addAll(b, jsonObject.toJSONString().getBytes()), subarray);webSocket.send(new ByteString(bytes));}}System.out.println("all data is send");} catch (Exception e) {e.printStackTrace();} finally {if (fileInputStream != null) {try {fileInputStream.close();} catch (IOException e) {e.printStackTrace();}}if (byteOut != null) {try {byteOut.close();} catch (IOException e) {e.printStackTrace();}}}}).start();}@Overridepublic void onMessage(WebSocket webSocket, String text) {super.onMessage(webSocket, text);}@Overridepublic void onMessage(WebSocket webSocket, ByteString bytes) {super.onMessage(webSocket, bytes);byte[] byteArray = bytes.toByteArray();// byte[]转lengthint length = (byteArray[0] << 24) + (byteArray[1] << 16) + (byteArray[2] << 8) + byteArray[3];byte[] jsonArray = ArrayUtils.subarray(byteArray, 4, 4 + length);String jsonStr = new String(jsonArray);JSONObject jsonObject = JSONObject.parseObject(jsonStr);byte[] subarray = ArrayUtils.subarray(byteArray, 4 + length, byteArray.length);File resultPcmFile = new File(dic, new File(pcmFile).getName().replace(".pcm", "_result.pcm"));if (!resultPcmFile.exists()) {try {resultPcmFile.createNewFile();} catch (IOException e) {e.printStackTrace();}}try {// 写入文件FileOutputStream outputStream = new FileOutputStream(resultPcmFile, true);IOUtils.write(subarray, outputStream);IOUtils.closeQuietly(outputStream);if ((int) jsonObject.get("errcode") == 0) {if (jsonObject.getBoolean("lastpkg")) {//说明数据全部返回完毕，可以关闭连接，释放资源System.out.println("session end ");System.out.println(sdf.format(startTime) + "开始");System.out.println(sdf.format(timeEnd.get()) + "结束");System.out.println("耗时:" + (timeEnd.get().getTime() - startTime.getTime()) + "ms");System.out.println("本次识别traceId ==》" + jsonObject.getString("traceid"));webSocket.close(1000, "");}} else {System.out.println("errCode=>" + jsonObject.getInteger("errcode") + " errMsg=>" + jsonObject.getString("errmsg") + " traceId=" + jsonObject.getString("traceid"));// 关闭连接webSocket.close(1000, "");System.out.println("发生错误，关闭连接");return;}} catch (Exception e) {e.printStackTrace();}}@Overridepublic void onFailure(WebSocket webSocket, Throwable t, Response response) {super.onFailure(webSocket, t, response);try {if (null != response) {int code = response.code();System.out.println("onFailure code:" + code);System.out.println("onFailure body:" + response.body().string());}} catch (IOException e) {// TODO Auto-generated catch blocke.printStackTrace();}}public static void main(String[] args) {OkHttpClient client = new OkHttpClient.Builder().build();Request request = new Request.Builder().url(hostUrl).build();client.newWebSocket(request, new VcWebSocketDemo());}public static String getAccessToken() {String accessToken = "";OkHttpClient client = new OkHttpClient();// request 默认是get请求String url = String.format(tokenUrl, clientSecret, clientId);Request request = new Request.Builder().url(url).build();JSONObject jsonObject;try {Response response = client.newCall(request).execute();if (response.isSuccessful()) {// 解析String resultJson = response.body().string();jsonObject = JSON.parseObject(resultJson);accessToken = jsonObject.getString("access_token");}} catch (Exception e) {e.printStackTrace();}return accessToken;}}
如果觉得《手把手教你用JAVA调用Websocket实现“声音转换”功能（变声）标贝科技》对你有帮助，请点赞、收藏，并留下你的观点哦！
