Vue+SpringBoot+Audio+科大讯飞语音合成技术_科大讯飞 tts springboot

作者：盐析白兔 | 2024-05-03 19:25:21

踩

科大讯飞 tts springboot

最终思路

思路就是vue前端向后台发送需要播放的语音信息(文字),然后后台返回语音流数据,通过URL.createObjectURL(data) 这个API生成一个URL，然后给audio标签附上url，网页进行语音播放，在网页播放语音就可以避免用户的本地语音库的安装。

在Vue项目中用Audio实现语音的播放（基础版）


1.axios 拦截处理
// respone拦截器
service.interceptors.response.use(
    response => {
 
        const headers = response.headers
        if (headers['content-type'] === 'application/octet-stream;charset=UTF-8') {
            return response.data
        }
    }
)
 
2.接口请求
/**
 * 文字转语音接口
 */
export function textToAudio(text) {
    let jsonData = {
        text: text,
    }
    return request({
        url: '/api/audio/text_to_audio',
        method: 'post',
        data: Qs.stringify(jsonData),
        responseType: "blob"//后台返回的为语音的流数据
    })
}
3.请求后台接口
//调用后台
getAudio(text) {
    textToAudio(text).then(response => {
        let url = URL.createObjectURL(response);//通过这个API让语音数据转为成一个url地址
        let audio = new Audio();//在VUE中使用audio标签
        audio.src = url;//设置audio的src为上面生成的url
        let playPromiser = audio.play();//进行播放
        //在谷歌内核中,audio.play()会返回一个promise的值，在IE内核中就不会返回任何的值
        //所以如果你要分浏览器，可以判断playPromiser的值来进行操作哦
        audio.onended = () => {
            //onended可以检测语音是否播完
            //dosometin
        };
    }).catch(err => {});
},

4.springboot


@ApiOperation(value = "文字转语音", notes = "文字转语音")
@RequestMapping(value = "text_to_audio")
public void textToAudio(String text, HttpServletRequest request , HttpServletResponse response) throws IOException {
    if (StringUtils.isNotBlank(text)) {
            //过滤图片,h5标签
            text = text.replaceAll("\\&[a-zA-Z]{1,10};", "").replaceAll("<[^>]*>", "").replaceAll("[(/>)<]", "").trim();
            //调用微服务接口获取音频base64
            String result = "";
            try {
                JSONObject json = new JSONObject();
                JSONObject params = new JSONObject();
                params.put("content", text);
                json.put("params", params);
                String resultStr = HttpClientUtil.postJson(TEXT_TO_ADUIO, json.toString());
                JSONObject resultJson = JSON.parseObject(resultStr);
                System.out.println(resultJson.toJSONString());
                boolean success = resultJson.getInteger("result") == 0;
                if (!success) {
                    throw new ExternalCallException(resultJson.getString("message"));
                }
                result = resultJson.getJSONArray("datas").getJSONObject(0).getString("audioBase64");
            } catch (Exception e) {
                log.error("【文字转语音接口调用异常】", e);
//                throw new ExternalCallException(e.getMessage());
            }
            //音频数据
            byte[] audioByte = Base64.getDecoder().decode(result);
 
            response.setContentType("application/octet-stream;charset=UTF-8");
            OutputStream os = new BufferedOutputStream(response.getOutputStream());
            SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMddHHmmssSSS");
            String date = sdf.format(new Date());
            try {
                   //音频流
                    os.write(audioByte);
            } catch (IOException e) {
                e.printStackTrace();
            } finally {
                if (os != null) {
                    os.flush();
                    os.close();
                }
            }
        }
}

防止因为快速的请求语音数据造成语音播放叠在一起


data() {
    return {
  audio:true,
  callmsg:[],
    }
}


//排队队列   data 是文本信息
queue(data){
    this.callmsg.push(data);//this.callmsg就是排队队列,点击一次，放进去一个需要播放的信息
    if (this.audio) {//如果没人
        this.audio = false;//改为有人排队了
        this.getAudio();//进行播放操作
    }
 
},
//语音播放
getAudio() {
    if (this.callmsg.length > 0) {//如果队列是有人在排队的，这进行播放操作
    textToAudio(this.callmsg[0]).then(response => {
        let url = URL.createObjectURL(response);//通过这个API让语音数据转为成一个url地址
        let audio = new Audio();//在VUE中使用audio标签
        audio.src = url;//设置audio的src为上面生成的url
        let playPromiser = audio.play();//进行播放
        //在这里我用一个标志，设置语音开始播放
       /* localStorage.setItem("audio", "1");*/
        //在谷歌内核中,audio.play()会返回一个promise的值，在IE内核中就不会返回任何的值
        //所以如果你要分浏览器，可以判断playPromiser的值来进行操作哦
        audio.onended = () => {
            //onended可以检测语音是否播完
            //dosometing
            this.callmsg.splice(0, 1);//队列的第一个播放完毕，所以删除
           /* localStorage.setItem("audio", "0");//这里是语音播放完毕*/
            this.getAudio();//进行下一个请求并播放
        };
    }).catch(err => {});
 
    } else {
        //this.audio是一个data数据,用来记录是否有人排队
        this.audio = true; //如果队列没人排队，就告诉外面已经读完啦
    }
},

最终实现前端功能代码


<!--语音播放-->
<template>
    <div class="audio">
        <div>
        <svg-icon v-if="audioPlayVisible" icon-class="play" @click.native="pause"
                  :class="{'audio-play-style':true, 'audio-play-style-pc': pc}"/>
        <svg-icon v-if="!audioPlayVisible" icon-class="stop_play" @click.native="play"
                  :class="{'audio-play-style':true, 'audio-play-style-pc': pc}"/>
        </div>
    </div>
</template>
<script>
    import {textToAudio} from '@/api/file'
    import {isPc} from '@/utils/common'
    export default {
        name: "audioPlay",
        props: {},
        components: {},
        mounted() {
             this.audioObj = new Audio();//在VUE中使用audio标签
        },
        created() {
 
        },
        data() {
            return {
                //语音播放开关
                audioPlayVisible: true,
                mAudioVisible: true,
                // 是否是PC端
                pc: isPc(),
                audioObj:null
            }
        },
        methods: {
            //暂停
            pause() {
               this.audioObj.pause();
               this.audioPlayVisible=false;
            },
            //播放
            play(){
                this.audioPlayVisible=true;
            },
            //调用后台
            getAudio(text) {
              if(!this.audioPlayVisible){
                  return
              }
                textToAudio(text).then(response => {
                    console.log('response', response)
                    let url = URL.createObjectURL(response);//通过这个API让语音数据转为成一个url地址
                    this.audioObj.src = url;//设置audio的src为上面生成的url
                    let playPromiser = this.audioObj.play();//进行播放
                    //在谷歌内核中,audio.play()会返回一个promise的值，在IE内核中就不会返回任何的值
                    //所以如果你要分浏览器，可以判断playPromiser的值来进行操作哦
                    this.audioObj.onended = () => {
                    };
                }).catch(err => {});
            },
        }
    }
</script>
 
<style lang="less">
    .audio {
 
        .audio-play-style {
            position: absolute;
            top: 10px;
            right: 0;
            font-size: 26px;
 
        }
        .audio-play-style-pc {
            top: 65px;
        }
    }
</style>

// 音频方式二 ----- 初始化
audioInit() {
    let AudioContext = window.AudioContext || window.webkitAudioContext
    if (AudioContext) {
        this.audioContext = new AudioContext()
        this.audioContext.resume()
    }
},

/**
 *  AudioContext 播放方式
 *
 * @param response  后台返回音频流
 */
playAudioMethodTwo(response) {
    var _this=this;
    //将Blob音频流转换成 ArrayBuffer
    var reader = new FileReader();
    reader.readAsArrayBuffer(response);
    reader.onload = function (e) {
        let arrayBuffer=reader.result;
        _this.audioContext.decodeAudioData(arrayBuffer).then(function (buffer) {
            var source = _this.audioContext.createBufferSource();
            source.buffer = buffer;
            source.connect(_this.audioContext.destination);
            source.start();
        }, function (e) {
            console.log("FAIL:" + arrayBuffer);
        });
    }
},

科大讯飞java 流demo 接口

注意事项：记得导入相关依赖包，hutool 直接maven库搜索

package com.ylz.springboot.modules.external.service.impl;

import com.google.common.collect.Lists;

import com.google.gson.Gson; import com.google.gson.JsonObject; import okhttp3.*; import okio.ByteString; import org.springframework.data.redis.util.ByteUtils;

import javax.crypto.Mac; import javax.crypto.spec.SecretKeySpec; import java.io.IOException; import java.io.UnsupportedEncodingException; import java.net.URL; import java.nio.charset.Charset; import java.text.SimpleDateFormat; import java.util.*;

/** * 科大讯飞语音合成 * * @author lhh * @Date 2020/5/7 11:06 */ public class WebTTSWS { private static final String hostUrl = "https://tts-api.xfyun.cn/v2/tts"; //http url 不支持解析 ws/wss schema private static final String appid = "xxxx";//到控制台-语音合成页面获取 private static final String apiSecret = "xxxxxx";//到控制台-语音合成页面获取 private static final String apiKey = "xxxx";//到控制台-语音合成页面获取 private static final String text = "蜡烛有心，杨柳有心，于是它能低首沉思"; public static String base64 = ""; public static final Gson json = new Gson(); private volatile boolean lock = true;

public static void main(String[] args) throws Exception { for (int i = 0; i < 1; i++) { new Thread(() -> { WebTTSWS w = new WebTTSWS(); try { String send = w.send(); System.out.println(send); } catch (Exception e) { e.printStackTrace(); } }).start(); } }

public String send() throws Exception { lock = true; base64 = ""; // 构建鉴权url String authUrl = getAuthUrl(hostUrl, apiKey, apiSecret); OkHttpClient client = new OkHttpClient.Builder().build(); //将url中的 schema http://和https://分别替换为ws:// 和 wss:// String url = authUrl.toString().replace("http://", "ws://").replace("https://", "wss://"); Request request = new Request.Builder().url(url).build();

List<byte[]> list = Lists.newArrayList(); WebSocket webSocket = client.newWebSocket(request, new WebSocketListener() { @Override public void onOpen(WebSocket webSocket, Response response) { super.onOpen(webSocket, response); try { System.out.println(response.body().string()); } catch (IOException e) { e.printStackTrace(); } //发送数据 JsonObject frame = new JsonObject(); JsonObject business = new JsonObject(); JsonObject common = new JsonObject(); JsonObject data = new JsonObject(); // 填充common common.addProperty("app_id", appid); //填充business business.addProperty("aue", "lame"); business.addProperty("sfl", 1); business.addProperty("tte", "UTF8");//小语种必须使用UNICODE编码 business.addProperty("vcn", "aisxping");//到控制台-我的应用-语音合成-添加试用或购买发音人，添加后即显示该发音人参数值，若试用未添加的发音人会报错11200 business.addProperty("pitch", 50); business.addProperty("speed", 50); //填充data data.addProperty("status", 2);//固定位2 try { data.addProperty("text", Base64.getEncoder().encodeToString(text.getBytes("utf8"))); //使用小语种须使用下面的代码，此处的unicode指的是 utf16小端的编码方式，即"UTF-16LE"” //data.addProperty("text", Base64.getEncoder().encodeToString(text.getBytes("UTF-16LE"))); } catch (UnsupportedEncodingException e) { e.printStackTrace(); } //填充frame frame.add("common", common); frame.add("business", business); frame.add("data", data); webSocket.send(frame.toString()); }

@Override public void onMessage(WebSocket webSocket, String text) { super.onMessage(webSocket, text); //处理返回数据 System.out.println("receive=>" + text); ResponseData resp = null; try { resp = json.fromJson(text, ResponseData.class); } catch (Exception e) { e.printStackTrace(); } if (resp != null) { if (resp.getCode() != 0) { System.out.println("error=>" + resp.getMessage() + " sid=" + resp.getSid()); return; } if (resp.getData() != null) { String result = resp.getData().audio; byte[] audio = Base64.getDecoder().decode(result); list.add(audio); // todo resp.data.status ==2 说明数据全部返回完毕，可以关闭连接，释放资源 if (resp.getData().status == 2) { String is = base64Concat(list); base64 = is; lock = false; webSocket.close(1000, ""); } } } }

@Override public void onMessage(WebSocket webSocket, ByteString bytes) { super.onMessage(webSocket, bytes); }

@Override public void onClosing(WebSocket webSocket, int code, String reason) { super.onClosing(webSocket, code, reason); System.out.println("socket closing"); }

@Override public void onClosed(WebSocket webSocket, int code, String reason) { super.onClosed(webSocket, code, reason); System.out.println("socket closed"); }

@Override public void onFailure(WebSocket webSocket, Throwable t, Response response) { super.onFailure(webSocket, t, response); System.out.println("connection failed" + response.message()); } });

while (lock) { } return base64; }

/** * base64拼接 */ String base64Concat(List<byte[]> list) { int length = 0; for (byte[] b : list) { length += b.length; } byte[] retByte = new byte[length]; for (byte[] b : list) { retByte = ByteUtils.concat(retByte, b); } return cn.hutool.core.codec.Base64.encode(retByte); }

/** * 获取权限地址 * * @param hostUrl * @param apiKey * @param apiSecret * @return */ public static String getAuthUrl(String hostUrl, String apiKey, String apiSecret) throws Exception { URL url = new URL(hostUrl); SimpleDateFormat format = new SimpleDateFormat("EEE, dd MMM yyyy HH:mm:ss z", Locale.US); format.setTimeZone(TimeZone.getTimeZone("GMT")); String date = format.format(new Date()); StringBuilder builder = new StringBuilder("host: ").append(url.getHost()).append("\n"). append("date: ").append(date).append("\n"). append("GET ").append(url.getPath()).append(" HTTP/1.1"); Charset charset = Charset.forName("UTF-8"); Mac mac = Mac.getInstance("hmacsha256"); SecretKeySpec spec = new SecretKeySpec(apiSecret.getBytes(charset), "hmacsha256"); mac.init(spec); byte[] hexDigits = mac.doFinal(builder.toString().getBytes(charset)); String sha = Base64.getEncoder().encodeToString(hexDigits); String authorization = String.format("hmac username=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"", apiKey, "hmac-sha256", "host date request-line", sha); HttpUrl httpUrl = HttpUrl.parse("https://" + url.getHost() + url.getPath()).newBuilder(). addQueryParameter("authorization", Base64.getEncoder().encodeToString(authorization.getBytes(charset))). addQueryParameter("date", date). addQueryParameter("host", url.getHost()). build(); return httpUrl.toString(); }

public static class ResponseData { private int code; private String message; private String sid; private Data data;

public int getCode() { return code; }

public String getMessage() { return this.message; }

public String getSid() { return sid; }

public Data getData() { return data; } }

public static class Data { //标志音频是否返回结束 status=1，表示后续还有音频返回，status=2表示所有的音频已经返回 private int status; //返回的音频，base64 编码 private String audio; // 合成进度 private String ced; }

}

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/盐析白兔/article/detail/531161

Vue+SpringBoot+Audio+科大讯飞 语音合成技术_科大讯飞 tts springboot

最终思路

在Vue项目中用Audio实现语音的播放（基础版）

防止因为快速的请求语音数据造成语音播放叠在一起

Vue+SpringBoot+Audio+科大讯飞语音合成技术_科大讯飞 tts springboot