调用火山云的语音生成TTS和语音识别STT

首先需要去火山云的控制台开通TTS和STT服务语音技术 (volcengine.com)

火山这里都提供了免费的额度可以使用

我这里是使用了java来调用API

目前我还了解到阿里的开源项目SenseVoice（STT）和CosyVoice(TTS)非常的不错，但是都是使用Python开发的。可以做到说话情绪的识别，感兴趣可以去github上了解一下。

TTS（首先需要导入它给的类）

package com.erroright.backend_server_java.pojo.util;

import java.util.UUID;

public class TtsRequest {
    public static final String APP_ID = "控制台的APPID";
    public static final String CLUSTER = "";

    public static final String Token = "";
    public static final String VoiceType = "BV001_streaming";//生成声音的选择（如果生成语音报错，就是你没开通这个音色的权限）
    public static final String Emotion = "angry";//语气




    public TtsRequest() {
    }

    public TtsRequest(String text) {
        this.request.text = text;
    }

    private App app = new App();
    private User user = new User();
    private Audio audio = new Audio();
    private Request request = new Request();

    public App getApp() {
        return app;
    }

    public void setApp(App app) {
        this.app = app;
    }

    public User getUser() {
        return user;
    }

    public void setUser(User user) {
        this.user = user;
    }

    public Audio getAudio() {
        return audio;
    }

    public void setAudio(Audio audio) {
        this.audio = audio;
    }

    public Request getRequest() {
        return request;
    }

    public void setRequest(Request request) {
        this.request = request;
    }

    public class App {
        private String appid = APP_ID;
        private String token = Token; // 目前未生效，填写默认值：access_token
        private String cluster = CLUSTER;

        public String getAppid() {
            return appid;
        }

        public void setAppid(String appid) {
            this.appid = appid;
        }

        public String getToken() {
            return token;
        }

        public void setToken(String token) {
            this.token = token;
        }

        public String getCluster() {
            return cluster;
        }

        public void setCluster(String cluster) {
            this.cluster = cluster;
        }
    }

    public class User {
        private String uid = "388808087185088"; // 目前未生效，填写一个默认值就可以

        public String getUid() {
            return uid;
        }

        public void setUid(String uid) {
            this.uid = uid;
        }
    }

    public class Audio {
        private String voice_type = VoiceType;
        private String encoding = "wav";
        private float speed_ratio = 1.0F;
        private float volume_ratio = 10;
        private float pitch_ratio = 10;
        private String emotion = Emotion;

        public String getVoice_type() {
            return voice_type;
        }

        public void setVoice_type(String voice_type) {
            this.voice_type = voice_type;
        }

        public String getEncoding() {
            return encoding;
        }

        public void setEncoding(String encoding) {
            this.encoding = encoding;
        }

        public float getSpeedRatio() {
            return speed_ratio;
        }

        public void setSpeedRatio(int speed_ratio) {
            this.speed_ratio = speed_ratio;
        }

        public float getVolumeRatio() {
            return volume_ratio;
        }

        public void setVolumeRatio(int volume_ratio) {
            this.volume_ratio = volume_ratio;
        }

        public float getPitchRatio() {
            return pitch_ratio;
        }

        public void setPitchRatio(int pitch_ratio) {
            this.pitch_ratio = pitch_ratio;
        }

        public String getEmotion() {
            return emotion;
        }

        public void setEmotion(int emotion) {
            this.emotion = String.valueOf(emotion);
        }
    }

    public class Request {
        private String reqid = UUID.randomUUID().toString();
        private String text;
        private String text_type = "plain";
        private String operation = "query";

        public String getReqid() {
            return reqid;
        }

        public void setReqid(String reqid) {
            this.reqid = reqid;
        }

        public String getText() {
            return text;
        }

        public void setText(String text) {
            this.text = text;
        }

        public String getText_type() {
            return text_type;
        }

        public void setText_type(String text_type) {
            this.text_type = text_type;
        }

        public String getOperation() {
            return operation;
        }

        public void setOperation(String operation) {
            this.operation = operation;
        }
    }
}

调用代码

package com.erroright.backend_server_java.util;

import com.alibaba.fastjson.JSON;
import com.erroright.backend_server_java.pojo.util.TtsRequest;
import lombok.extern.slf4j.Slf4j;
import okhttp3.*;
import org.springframework.stereotype.Component;


import java.io.FileOutputStream;
import java.io.IOException;
import java.util.Base64;

@Component
@Slf4j
public class TtsHttpClient {


    public static final String API_URL = "https://openspeech.bytedance.com/api/v1/tts";
    public static final String ACCESS_TOKEN = "填入火山云开通项目的Token";


    public static byte[] getTts(String content) throws IOException {
        log.info("TTS生成："+content);
        TtsRequest ttsRequest = new TtsRequest(content);
        String json= JSON.toJSONString(ttsRequest);
        OkHttpClient client = new OkHttpClient();
        RequestBody body = RequestBody.create(json, MediaType.get("application/json; charset=utf-8"));
        Request request = new Request.Builder()
                .url(API_URL)
                .post(body)
                .header("Authorization", "Bearer; " + ACCESS_TOKEN)
                .build();
        try (Response response = client.newCall(request).execute()) {
            String TtsRresponse=response.body().string();
            // 提取 "data" 字段的值
            String data = TtsRresponse.split("\"data\":\"")[1].split("\"")[0];
               //保存生成的文件
            try (FileOutputStream fos = new FileOutputStream("output.wav")) {
                fos.write(Base64.getDecoder().decode(data));
            }
            // 解码 Base64 数据
            return Base64.getDecoder().decode(data);
        }
    }

}

STT(导入类，在官方文档中是三个类，为了在springBoot中封装，分开了一个)
 

package com.erroright.backend_server_java.pojo.util;

import com.fasterxml.jackson.databind.DeserializationFeat