Intelligent Speech Interaction:RESTful API

Dépendances

Ajoutez les dépendances suivantes au fichier pom.xml de votre projet Maven :

<dependency>
    <groupId>com.squareup.okhttp3</groupId>
    <artifactId>okhttp</artifactId>
    <version>3.9.1</version>
</dependency>
<!-- http://mvnrepository.com/artifact/com.alibaba/fastjson -->
<dependency>
    <groupId>com.alibaba</groupId>
    <artifactId>fastjson</artifactId>
    <version>1.2.83</version>
</dependency>
<dependency>
    <groupId>org.asynchttpclient</groupId>
    <artifactId>async-http-client</artifactId>
    <version>2.5.4</version>
</dependency>

Requêtes standard

import java.io.File;
import java.io.FileOutputStream;
import java.io.UnsupportedEncodingException;
import java.net.URLEncoder;
import com.alibaba.fastjson.JSONObject;
import okhttp3.MediaType;
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.RequestBody;
import okhttp3.Response;
public class SpeechSynthesizerRestfulDemo {
    private String accessToken;
    private String appkey;
    public SpeechSynthesizerRestfulDemo(String appkey, String token) {
        this.appkey = appkey;
        this.accessToken = token;
    }
    /**
     * HTTPS GET request
     */
    public void processGETRequet(String text, String audioSaveFile, String format, int sampleRate, String voice) {
        /**
         * Configure the HTTPS GET request:
         * 1. Use the HTTPS protocol.
         * 2. Speech Synthesis service domain name: nls-gateway-ap-southeast-1.aliyuncs.com
         * 3. Speech Synthesis API request path: /stream/v1/tts
         * 4. Set the parameters used in this example: appkey, token, text, format, and sample_rate.
         * 5. Set the optional request parameters: voice, volume, speech_rate, and pitch_rate.
         */
        String url = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts";
        url = url + "?appkey=" + appkey;
        url = url + "&token=" + accessToken;
        url = url + "&text=" + text;
        url = url + "&format=" + format;
        url = url + "&voice=" + voice;
        url = url + "&sample_rate=" + String.valueOf(sampleRate);
        // voice: The speaker's voice. Optional. Default value: xiaoyun.
        // url = url + "&voice=" + "xiaoyun";
        // volume: The volume. The value ranges from 0 to 100. Optional. Default value: 50.
        // url = url + "&volume=" + String.valueOf(50);
        // speech_rate: The speech rate. The value ranges from -500 to 500. Optional. Default value: 0.
        // url = url + "&speech_rate=" + String.valueOf(0);
        // pitch_rate: The pitch rate. The value ranges from -500 to 500. Optional. Default value: 0.
        // url = url + "&pitch_rate=" + String.valueOf(0);
        /**
         * Send the HTTPS GET request and process the response from the server.
         */
        Request request = new Request.Builder().url(url).get().build();
        try {
            long start = System.currentTimeMillis();
            OkHttpClient client = new OkHttpClient();
            Response response = client.newCall(request).execute();
            System.out.println("total latency :" + (System.currentTimeMillis() - start) + " ms");
            System.out.println(response.headers().toString());
            String contentType = response.header("Content-Type");
            if ("audio/mpeg".equals(contentType)) {
                File f = new File(audioSaveFile);
                FileOutputStream fout = new FileOutputStream(f);
                fout.write(response.body().bytes());
                fout.close();
                System.out.println("The GET request succeeded!");
            }
            else {
                // The Content-Type is null or "application/json".
                String errorMessage = response.body().string();
                System.out.println("The GET request failed: " + errorMessage);
            }
            response.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
    /**
     * HTTPS POST request
     */
    public void processPOSTRequest(String text, String audioSaveFile, String format, int sampleRate, String voice) {
        /**
         * Configure the HTTPS POST request:
         * 1. Use the HTTPS protocol.
         * 2. Speech Synthesis service domain name: nls-gateway-ap-southeast-1.aliyuncs.com
         * 3. Speech Synthesis API request path: /stream/v1/tts
         * 4. Set the parameters used in this example: appkey, token, text, format, and sample_rate.
         * 5. Set the optional request parameters: voice, volume, speech_rate, and pitch_rate.
         */
        String url = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts";
        JSONObject taskObject = new JSONObject();
        taskObject.put("appkey", appkey);
        taskObject.put("token", accessToken);
        taskObject.put("text", text);
        taskObject.put("format", format);
        taskObject.put("voice", voice);
        taskObject.put("sample_rate", sampleRate);
        // voice: The speaker's voice. Optional. Default value: xiaoyun.
        // taskObject.put("voice", "xiaoyun");
        // volume: The volume. The value ranges from 0 to 100. Optional. Default value: 50.
        // taskObject.put("volume", 50);
        // speech_rate: The speech rate. The value ranges from -500 to 500. Optional. Default value: 0.
        // taskObject.put("speech_rate", 0);
        // pitch_rate: The pitch rate. The value ranges from -500 to 500. Optional. Default value: 0.
        // taskObject.put("pitch_rate", 0);
        String bodyContent = taskObject.toJSONString();
        RequestBody reqBody = RequestBody.create(MediaType.parse("application/json"), bodyContent);
        Request request = new Request.Builder()
            .url(url)
            .header("Content-Type", "application/json")
            .post(reqBody)
            .build();
        try {
            OkHttpClient client = new OkHttpClient();
            Response response = client.newCall(request).execute();
            String contentType = response.header("Content-Type");
            if ("audio/mpeg".equals(contentType)) {
                File f = new File(audioSaveFile);
                FileOutputStream fout = new FileOutputStream(f);
                fout.write(response.body().bytes());
                fout.close();
                System.out.println("The POST request succeeded!");
            }
            else {
                // The Content-Type is null or "application/json".
                String errorMessage = response.body().string();
                System.out.println("The POST request failed: " + errorMessage);
            }
            response.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
    public static void main(String[] args) {
        if (args.length < 2) {
            System.err.println("SpeechSynthesizerRestfulDemo needs params: <token> <app-key>");
            System.exit(-1);
        }
        String token = args[0];
        String appkey = args[1];
        SpeechSynthesizerRestfulDemo demo = new SpeechSynthesizerRestfulDemo(appkey, token);
        String text = "Today is Monday. The weather is nice.";
        // URL-encode the text based on RFC 3986.
        String textUrlEncode = text;
        try {
            textUrlEncode = URLEncoder.encode(textUrlEncode, "UTF-8")
                .replace("+", "%20")
                .replace("*", "%2A")
                .replace("%7E", "~");
        } catch (UnsupportedEncodingException e) {
            e.printStackTrace();
        }
        System.out.println(textUrlEncode);
        String audioSaveFile = "syAudio.wav";
        String format = "wav";
        int sampleRate = 16000;
        demo.processGETRequet(textUrlEncode, audioSaveFile, format, sampleRate, "siyue");
        //demo.processPOSTRequest(text, audioSaveFile, format, sampleRate, "siyue");
        System.out.println("### Game Over ###");
    }
}

Réponses en continu

Recevez les fragments audio via des rappels de réponse. Maintenez ces rappels concis. Transférez l'audio à un autre thread pour sa lecture ou son traitement ultérieur.

import java.io.File;
import java.io.FileOutputStream;
import java.io.UnsupportedEncodingException;
import java.net.URLEncoder;
import java.util.concurrent.CountDownLatch;
import io.netty.handler.codec.http.HttpHeaders;
import org.asynchttpclient.AsyncHandler;
import org.asynchttpclient.AsyncHttpClient;
import org.asynchttpclient.AsyncHttpClientConfig;
import org.asynchttpclient.DefaultAsyncHttpClient;
import org.asynchttpclient.DefaultAsyncHttpClientConfig;
import org.asynchttpclient.HttpResponseBodyPart;
import org.asynchttpclient.HttpResponseStatus;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
 * This example demonstrates how to:
 * 1. Call the RESTful API for Speech Synthesis.
 * 2. Handle a streaming response by enabling HTTP chunked transfer encoding.
 */
public class SpeechSynthesizerRestfulChunkedDemo {
    private static Logger logger = LoggerFactory.getLogger(SpeechSynthesizerRestfulChunkedDemo.class);
    private String accessToken;
    private String appkey;
    public SpeechSynthesizerRestfulChunkedDemo(String appkey, String token) {
        this.appkey = appkey;
        this.accessToken = token;
    }
    public void processGETRequest(String text, String audioSaveFile, String format, int sampleRate, String voice, boolean chunked) {
        /**
         * Configure the HTTPS GET request:
         * 1. Protocol: HTTPS
         * 2. Speech Synthesis Endpoint: nls-gateway-ap-southeast-1.aliyuncs.com
         * 3. Request Path: /stream/v1/tts
         * 4. Parameters used in this example: appkey, token, text, format, and sample_rate
         * 5. Optional parameters: voice, volume, speech_rate, and pitch_rate
         * 6. Use the `chunk` parameter to enable HTTP chunked transfer encoding.
         */
        String url = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts";
        url = url + "?appkey=" + appkey;
        url = url + "&token=" + accessToken;
        url = url + "&text=" + text;
        url = url + "&format=" + format;
        url = url + "&voice=" + voice;
        url = url + "&sample_rate=" + String.valueOf(sampleRate);
        url = url + "&chunk=" + String.valueOf(chunked);
        try {
            AsyncHttpClientConfig config = new DefaultAsyncHttpClientConfig.Builder()
                .setConnectTimeout(3000)
                .setKeepAlive(true)
                .setReadTimeout(10000)
                .setRequestTimeout(50000)
                .setMaxConnections(1000)
                .setMaxConnectionsPerHost(200)
                .setPooledConnectionIdleTimeout(-1)
                .build();
            AsyncHttpClient httpClient = new DefaultAsyncHttpClient(config);
            CountDownLatch latch = new CountDownLatch(1);
            AsyncHandler<org.asynchttpclient.Response> handler = new AsyncHandler<org.asynchttpclient.Response>() {
                FileOutputStream outs;
                boolean firstRecvBinary = true;
                long startTime = System.currentTimeMillis();
                int httpCode = 200;
                @Override
                public State onStatusReceived(HttpResponseStatus httpResponseStatus) throws Exception {
                    logger.info("onStatusReceived status {}", httpResponseStatus);
                    httpCode = httpResponseStatus.getStatusCode();
                    if (httpResponseStatus.getStatusCode() != 200) {
                        logger.error("request error " +  httpResponseStatus.toString());
                    }
                    return State.CONTINUE;
                }
                @Override
                public State onHeadersReceived(HttpHeaders httpHeaders) throws Exception {
                    if (httpCode != 200 || !"audio/mpeg".equals(httpHeaders.get("Content-Type"))) {
                        throw new java.io.IOException("Unexpected synthesis response: HTTP " + httpCode);
                    }
                    outs = new FileOutputStream(new File(audioSaveFile));
                    return State.CONTINUE;
                }
                @Override
                public State onBodyPartReceived(HttpResponseBodyPart httpResponseBodyPart) throws Exception {
                    // Note: For improved responsiveness, play or process the audio stream immediately upon receiving the first data chunk.
                    // Note: Do not perform time-consuming operations in this callback. Push the binary Speech Synthesis audio stream to another thread asynchronously or by using a queue.
                    logger.info("onBodyPartReceived " + httpResponseBodyPart.getBodyPartBytes().toString());
                    if(httpCode != 200) {
                        System.err.write(httpResponseBodyPart.getBodyPartBytes());
                    }
                    if (firstRecvBinary) {
                        firstRecvBinary = false;
                        // Track the First Packet Latency. You can start audio processing (e.g., playback or sending to the caller) as soon as the first packet is received.
                        // Note: This First Packet Latency also includes the time to establish the network connection.
                        logger.info("tts first latency " + (System.currentTimeMillis() - startTime) + " ms");
                    }
                    // In this example, the audio stream is saved to a file.
                    outs.write(httpResponseBodyPart.getBodyPartBytes());
                    return State.CONTINUE;
                }
                @Override
                public void onThrowable(Throwable throwable) {
                    logger.error("Synthesis request failed: {}", throwable.getClass().getSimpleName());
                    if (outs != null) {
                        try { outs.close(); } catch (java.io.IOException ignored) { }
                    }
                    latch.countDown();
                }
                @Override
                public org.asynchttpclient.Response onCompleted() throws Exception {
                    logger.info("completed");
                    logger.info("tts total latency " + (System.currentTimeMillis() - startTime) + " ms");
                    outs.close();
                    latch.countDown();
                    return null;
                }
            };
            httpClient.prepareGet(url).execute(handler);
            // Wait for the synthesis to complete.
            latch.await();
            httpClient.close();
        }catch (Exception e) {
        }
    }
    public static void main(String[] args) {
        if (args.length < 2) {
            System.err.println("SpeechSynthesizerRestfulDemo requires the following parameters:  ");
            System.exit(-1);
        }
        String token = args[0];
        String appkey = args[1];
        SpeechSynthesizerRestfulChunkedDemo demo = new SpeechSynthesizerRestfulChunkedDemo(appkey, token);
        String text = "今天是周一，天气挺好的。";
        // URL-encode the text based on RFC 3986.
        String textUrlEncode = text;
        try {
            textUrlEncode = URLEncoder.encode(textUrlEncode, "UTF-8")
                .replace("+", "%20")
                .replace("*", "%2A")
                .replace("%7E", "~");
        } catch (UnsupportedEncodingException e) {
            e.printStackTrace();
        }
        System.out.println(textUrlEncode);
        String audioSaveFile = "syAudio.wav";
        String format = "wav";
        int sampleRate = 16000;
        // Setting the last parameter to true enables HTTP chunked transfer encoding.
        demo.processGETRequest(textUrlEncode, audioSaveFile, format, sampleRate, "aixia", true);
        System.out.println("### Demo finished ###");
    }
}

Pour obtenir un exemple complet de découpage et de synthèse de textes longs, téléchargez nls-restful-java-demo.zip.

#ifdef _WIN32
#include <Windows.h>
#endif
#include <iostream>
#include <string>
#include <map>
#include <fstream>
#include <sstream>
#include "curl/curl.h"
#include "json/json.h"
using namespace std;
#ifdef _WIN32
string GBKToUTF8(const string &strGBK) {
    string strOutUTF8 = "";
    WCHAR * str1;
    int n = MultiByteToWideChar(CP_ACP, 0, strGBK.c_str(), -1, NULL, 0);
    str1 = new WCHAR[n];
    MultiByteToWideChar(CP_ACP, 0, strGBK.c_str(), -1, str1, n);
    n = WideCharToMultiByte(CP_UTF8, 0, str1, -1, NULL, 0, NULL, NULL);
    char * str2 = new char[n];
    WideCharToMultiByte(CP_UTF8, 0, str1, -1, str2, n, NULL, NULL);
    strOutUTF8 = str2;
    delete[] str1;
    str1 = NULL;
    delete[] str2;
    str2 = NULL;
    return strOutUTF8;
}
#endif
void stringReplace(string& src, const string& s1, const string& s2) {
    string::size_type pos = 0;
    while ((pos = src.find(s1, pos)) != string::npos) {
        src.replace(pos, s1.length(), s2);
        pos += s2.length();
    }
}
string urlEncode(const string& src) {
    CURL* curl = curl_easy_init();
    char* output = curl_easy_escape(curl, src.c_str(), src.size());
    string result(output);
    curl_free(output);
    curl_easy_cleanup(curl);
    return result;
}
size_t responseHeadersCallback(void* ptr, size_t size, size_t nmemb, void* userdata)
{
    map<string, string> *headers = (map<string, string>*)userdata;
    string line((char*)ptr, size * nmemb);
    string::size_type pos = line.find(':');
    if (pos != line.npos)
    {
        string name = line.substr(0, pos);
        string value = line.substr(pos + 2);
        size_t p = 0;
        if ((p = value.rfind('\r')) != value.npos) {
            value = value.substr(0, p);
        }
        headers->insert(make_pair(name, value));
    }
    return size * nmemb;
}
size_t responseBodyCallback(void* ptr, size_t size, size_t nmemb, void* userData) {
    size_t len = size * nmemb;
    char* pBuf = (char*)ptr;
    string* bodyContent = (string*)userData;
    (*bodyContent).append(string(pBuf, pBuf + len));
    return len;
}
int processGETRequest(string appKey, string token, string text, 
                      string audioSaveFile, string format, int sampleRate) {
    CURL* curl = NULL;
    CURLcode res;
    curl = curl_easy_init();
    if (curl == NULL) {
        return -1;
    }
    string url = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts";
    /**
     * Construct the request URL with parameters.
     */
    ostringstream oss;
    oss << url;
    oss << "?appkey=" << appKey;
    oss << "&token=" << token;
    oss << "&text=" << text;
    oss << "&format=" << format;
    oss << "&sample_rate=" << sampleRate;
    // voice: The voice for synthesis. Optional. Default: xiaoyun.
    // oss << "&voice=" << "xiaoyun";
    // volume: The output volume. Optional. Valid range: 0 to 100. Default: 50.
    // oss << "&volume=" << 50;
    // speech_rate: The speech rate. Optional. Valid range: -500 to 500. Default: 0.
    // oss << "&speech_rate=" << 0;
    // pitch_rate: The pitch. Optional. Valid range: -500 to 500. Default: 0.
    // oss << "&pitch_rate=" << 0;
    string request = oss.str();
    curl_easy_setopt(curl, CURLOPT_URL, request.c_str());
    /**
     * Set the callback function for response headers.
     */
    map<string, string> responseHeaders;
    curl_easy_setopt(curl, CURLOPT_HEADERFUNCTION, responseHeadersCallback);
    curl_easy_setopt(curl, CURLOPT_HEADERDATA, &responseHeaders);
    /**
     * Set the callback function for the response body.
     */
    string bodyContent = "";
    curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, responseBodyCallback);
    curl_easy_setopt(curl, CURLOPT_WRITEDATA, &bodyContent);
    /**
     * Send the HTTPS GET request.
     */
    res = curl_easy_perform(curl);
    /**
     * Release resources.
     */
    curl_easy_cleanup(curl);
    if (res != CURLE_OK) {
        cerr << "curl_easy_perform failed: " << curl_easy_strerror(res) << endl;
        return -1;
    }
    /**
     * Process the response from the server.
     */
    map<string, string>::iterator it = responseHeaders.find("Content-Type");
    if (it != responseHeaders.end() && it->second.compare("audio/mpeg") == 0) {
        ofstream fs;
        fs.open(audioSaveFile.c_str(), ios::out | ios::binary);
        if (!fs.is_open()) {
            cout << "Cannot open the audio save file.";
            return -1;
        }
        fs.write(bodyContent.c_str(), bodyContent.size());
        fs.close();
        cout << "GET request succeeded." << endl;
    }
    else {
        cout << "The GET request failed: " + bodyContent << endl;
        return -1;
    }
    return 0;
}
int processPOSTRequest(string appKey, string token, string text,
                       string audioSaveFile, string format, int sampleRate) {
    CURL* curl = NULL;
    CURLcode res;
    curl = curl_easy_init();
    if (curl == NULL) {
        return -1;
    }
    string url = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts";
    /**
     * Set the URL for the HTTPS POST request.
     */
    curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
    curl_easy_setopt(curl, CURLOPT_POST, 1L);
    /**
     * Set the request headers.
     */
    struct curl_slist* headers = NULL;
    // Content-Type
    headers = curl_slist_append(headers, "Content-Type:application/json");
    curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
    /**
     * Construct the request body.
     */
    Json::Value root;
    Json::FastWriter writer;
    root["appkey"] = appKey;
    root["token"] = token;
    root["text"] = text;
    root["format"] = format;
    root["sample_rate"] = sampleRate;
    // voice: The voice for synthesis. Optional. Default: xiaoyun.
    // root["voice"] = "xiaoyun";
    // volume: The output volume. Optional. Valid range: 0 to 100. Default: 50.
    // root["volume"] = 50;
    // speech_rate: The speech rate. Optional. Valid range: -500 to 500. Default: 0.
    // root["speech_rate"] = 0;
    // pitch_rate: The pitch. Optional. Valid range: -500 to 500. Default: 0.
    // root["pitch_rate"] = 0;
    string task = writer.write(root);
    curl_easy_setopt(curl, CURLOPT_POSTFIELDS, task.c_str());
    curl_easy_setopt(curl, CURLOPT_POSTFIELDSIZE, task.length());
    /**
     * Set the callback function for response headers.
     */
    map<string, string> responseHeaders;
    curl_easy_setopt(curl, CURLOPT_HEADERFUNCTION, responseHeadersCallback);
    curl_easy_setopt(curl, CURLOPT_HEADERDATA, &responseHeaders);
    /**
     * Set the callback function for the response body.
     */
    string bodyContent = "";
    curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, responseBodyCallback);
    curl_easy_setopt(curl, CURLOPT_WRITEDATA, &bodyContent);
    /**
     * Send the HTTPS POST request.
     */
    res = curl_easy_perform(curl);
    /**
     * Release resources.
     */
    curl_slist_free_all(headers);
    curl_easy_cleanup(curl);
    if (res != CURLE_OK) {
        cerr << "curl_easy_perform failed: " << curl_easy_strerror(res) << endl;
        return -1;
    }
    /**
     * Process the response from the server.
     */
    map<string, string>::iterator it = responseHeaders.find("Content-Type");
    if (it != responseHeaders.end() && it->second.compare("audio/mpeg") == 0) {
        ofstream fs;
        fs.open(audioSaveFile.c_str(), ios::out | ios::binary);
        if (!fs.is_open()) {
            cout << "Cannot open the audio save file.";
            return -1;
        }
        fs.write(bodyContent.c_str(), bodyContent.size());
        fs.close();
        cout << "The POST request succeeded." << endl;
    }
    else {
        cout << "The POST request failed: " + bodyContent << endl;
        return -1;
    }
    return 0;
}
int main(int argc, char* argv[]) {
    if (argc < 3) {
        cerr << "Invalid parameters. Usage: ./demo your_token your_appkey" << endl;
        return -1;
    }
    string token = argv[1];
    string appKey = argv[2];
    string text = "Today is Monday, and the weather is nice.";
#ifdef _WIN32
    text = GBKToUTF8(text);
#endif
    string textUrlEncode = urlEncode(text);
    stringReplace(textUrlEncode, "+", "%20");
    stringReplace(textUrlEncode, "*", "%2A");
    stringReplace(textUrlEncode, "%7E", "~");
    string audioSaveFile = "syAudio.wav";
    string format = "wav";
    int sampleRate = 16000;
    // Initialize cURL. This should be done only once per process.
    curl_global_init(CURL_GLOBAL_ALL);
    processGETRequest(appKey, token, textUrlEncode, audioSaveFile, format, sampleRate);
    //processPOSTRequest(appKey, token, text, audioSaveFile, format, sampleRate);
    curl_global_cleanup();
    return 0;
}

# -*- coding: UTF-8 -*-
# Import httplib for Python 2.x.
# import httplib
# Import http.client for Python 3.x.
import http.client
# Import urllib for Python 2.x.
# import urllib
# Import urllib.parse for Python 3.x.
import urllib.parse
import json
def processGETRequest(appKey, token, text, audioSaveFile, format, sampleRate) :
    host = 'nls-gateway-ap-southeast-1.aliyuncs.com'
    url = 'https://' + host + '/stream/v1/tts'
    # Set the request parameters in the URL.
    url = url + '?appkey=' + appKey
    url = url + '&token=' + token
    url = url + '&text=' + text
    url = url + '&format=' + format
    url = url + '&sample_rate=' + str(sampleRate)
    # voice: Optional. The voice. Default: xiaoyun.
    # url = url + '&voice=' + 'xiaoyun'
    # volume: Optional. The audio volume. Range: 0-100. Default: 50.
    # url = url + '&volume=' + str(50)
    # speech_rate: Optional. The speech rate. Range: -500 to 500. Default: 0.
    # url = url + '&speech_rate=' + str(0)
    # pitch_rate: Optional. The pitch. Range: -500 to 500. Default: 0.
    # url = url + '&pitch_rate=' + str(0)
    # Use httplib for Python 2.x.
    # conn = httplib.HTTPSConnection(host)
    # Use http.client for Python 3.x.
    conn = http.client.HTTPSConnection(host)
    conn.request(method='GET', url=url)
    # Process the server response.
    response = conn.getresponse()
    print('Response status and reason:')
    print(response.status ,response.reason)
    contentType = response.getheader('Content-Type')
    print(contentType)
    body = response.read()
    if 'audio/mpeg' == contentType :
        with open(audioSaveFile, mode='wb') as f:
            f.write(body)
        print('The GET request succeeded!')
    else :
        print('The GET request failed: ' + str(body))
    conn.close()
def processPOSTRequest(appKey, token, text, audioSaveFile, format, sampleRate) :
    host = 'nls-gateway-ap-southeast-1.aliyuncs.com'
    url = 'https://' + host + '/stream/v1/tts'
    # Set the HTTPS headers.
    httpHeaders = {
        'Content-Type': 'application/json'
        }
    # Set the HTTPS body.
    body = {'appkey': appKey, 'token': token, 'text': text, 'format': format, 'sample_rate': sampleRate}
    body = json.dumps(body)
    # Use httplib for Python 2.x.
    # conn = httplib.HTTPSConnection(host)
    # Use http.client for Python 3.x.
    conn = http.client.HTTPSConnection(host)
    conn.request(method='POST', url=url, body=body, headers=httpHeaders)
    # Process the server response.
    response = conn.getresponse()
    print('Response status and reason:')
    print(response.status ,response.reason)
    contentType = response.getheader('Content-Type')
    print(contentType)
    body = response.read()
    if 'audio/mpeg' == contentType :
        with open(audioSaveFile, mode='wb') as f:
            f.write(body)
        print('The POST request succeeded!')
    else :
        print('The POST request failed: ' + str(body))
    conn.close()
appKey = 'Your AppKey'
token = 'Your Token'
text = 'Today is Monday, and the weather is nice.'
# URL-encode the text per RFC 3986.
textUrlencode = text
# Use urllib.quote for Python 2.x.
# textUrlencode = urllib.quote(textUrlencode, '')
# Use urllib.parse.quote_plus for Python 3.x.
textUrlencode = urllib.parse.quote_plus(textUrlencode)
textUrlencode = textUrlencode.replace("+", "%20")
textUrlencode = textUrlencode.replace("*", "%2A")
textUrlencode = textUrlencode.replace("%7E", "~")
print('text: ' + textUrlencode)
audioSaveFile = 'syAudio.wav'
format = 'wav'
sampleRate = 16000
# GET Request
processGETRequest(appKey, token, textUrlencode, audioSaveFile, format, sampleRate)
# POST Request
# processPOSTRequest(appKey, token, text, audioSaveFile, format, sampleRate)

<?php
function processGETRequest($appkey, $token, $text, $audioSaveFile, $format, $sampleRate) {
    $url = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts";
    $url = $url . "?appkey=" . $appkey;
    $url = $url . "&token=" . $token;
    $url = $url . "&text=" . $text;
    $url = $url . "&format=" . $format;
    $url = $url . "&sample_rate=" . strval($sampleRate);
    // voice: The speaker. Optional. Default: xiaoyun.
    // $url = $url . "&voice=" . "xiaoyun";
    // volume: The audio volume. Optional. Valid range: 0 to 100. Default: 50.
    // $url = $url . "&volume=" . strval(50);
    // speech_rate: The speaking rate. Optional. Valid range: -500 to 500. Default: 0.
    // $url = $url . "&speech_rate=" . strval(0);
    // pitch_rate: The speech pitch. Optional. Valid range: -500 to 500. Default: 0.
    // $url = $url . "&pitch_rate=" . strval(0);
    $curl = curl_init();
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, TRUE);
    /**
     * Set the HTTPS GET URL.
     */
    curl_setopt($curl, CURLOPT_URL, $url);
    /**
     * Include headers in the HTTPS response.
     */
    curl_setopt($curl, CURLOPT_HEADER, TRUE);
    /**
     * Send the HTTPS GET request.
     */
    curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, TRUE);
    curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, 2);
    $response = curl_exec($curl);
    if ($response == FALSE) {
        print "curl_exec failed!\n";
        curl_close($curl);
        return;
    }
    /**
     * Process the response from the server.
     */
    $headerSize = curl_getinfo($curl, CURLINFO_HEADER_SIZE);
    $headers = substr($response, 0, $headerSize);
    $bodyContent = substr($response, $headerSize);
    curl_close($curl);
    if (stripos($headers, "Content-Type: audio/mpeg") != FALSE || stripos($headers, "Content-Type:audio/mpeg") != FALSE) {
        file_put_contents($audioSaveFile, $bodyContent);
        print "The GET request succeeded!\n";
    }
    else {
        print "The GET request failed: " . $bodyContent . "\n";
    }
}
function processPOSTRequest($appkey, $token, $text, $audioSaveFile, $format, $sampleRate) {
    $url = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts";
    /**
     * Add the request parameters to the request body as a JSON string.
     */
    $taskArr = array(
        "appkey" => $appkey,
        "token" => $token,
        "text" => $text,
        "format" => $format,
        "sample_rate" => $sampleRate
        // voice: The speaker. Optional. Default: xiaoyun.
        // "voice" => "xiaoyun",
        // volume: The audio volume. Optional. Valid range: 0 to 100. Default: 50.
        // "volume" => 50,
        // speech_rate: The speaking rate. Optional. Valid range: -500 to 500. Default: 0.
        // "speech_rate" => 0,
        // pitch_rate: The speech pitch. Optional. Valid range: -500 to 500. Default: 0.
        // "pitch_rate" => 0
    );
    $body = json_encode($taskArr);
    $curl = curl_init();
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, TRUE);
    /**
     * Set the HTTPS POST URL.
     */
    curl_setopt($curl, CURLOPT_URL, $url);
    curl_setopt($curl, CURLOPT_POST, TRUE);
    /**
     * Set the HTTPS POST request headers.
     * */
    $httpHeaders = array(
        "Content-Type: application/json"
    );
    curl_setopt($curl, CURLOPT_HTTPHEADER, $httpHeaders);
    /**
     * Set the HTTPS POST request body.
     */
    curl_setopt($curl, CURLOPT_POSTFIELDS, $body);
    /**
     * Include headers in the HTTPS response.
     */
    curl_setopt($curl, CURLOPT_HEADER, TRUE);
    /**
     * Send the HTTPS POST request.
     */
    $response = curl_exec($curl);
    if ($response == FALSE) {
        print "curl_exec failed!\n";
        curl_close($curl);
        return;
    }
    /**
     * Process the response from the server.
     */
    $headerSize = curl_getinfo($curl, CURLINFO_HEADER_SIZE);
    $headers = substr($response, 0, $headerSize);
    $bodyContent = substr($response, $headerSize);
    curl_close($curl);
    if (stripos($headers, "Content-Type: audio/mpeg") != FALSE || stripos($headers, "Content-Type:audio/mpeg") != FALSE) {
        file_put_contents($audioSaveFile, $bodyContent);
        print "The POST request succeeded!\n";
    }
    else {
        print "The POST request failed: " . $bodyContent . "\n";
    }
}
$appkey = "YOUR_APPKEY";
$token = "YOUR_TOKEN";
$text = "Today is Monday. The weather is nice.";
$textUrlEncode = urlencode($text);
$textUrlEncode = preg_replace('/\+/', '%20', $textUrlEncode);
$textUrlEncode = preg_replace('/\*/', '%2A', $textUrlEncode);
$textUrlEncode = preg_replace('/%7E/', '~', $textUrlEncode);
$audioSaveFile = "syAudio.wav";
$format = "wav";
$sampleRate = 16000;
processGETRequest($appkey, $token, $textUrlEncode, $audioSaveFile, $format, $sampleRate);
// processPOSTRequest($appkey, $token, $text, $audioSaveFile, $format, $sampleRate);
?>

npm install request --save

const request = require('request');
const fs = require('fs');
function processGETRequest(appkey, token, text, audioSaveFile, format, sampleRate) {
    var url = 'https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts';
    /**
     * Set the request parameters in the URL.
     */
    url = url + '?appkey=' + appkey;
    url = url + '&token=' + token;
    url = url + '&text=' + text;
    url = url + '&format=' + format;
    url = url + '&sample_rate=' + sampleRate;
    // voice: Optional. The synthesis voice. Default: xiaoyun.
    // url = url + "&voice=" + "xiaoyun";
    // volume: Optional. The audio volume. Range: 0–100. Default: 50.
    // url = url + "&volume=" + 50;
    // speech_rate: Optional. The speech rate. Range: -500–500. Default: 0.
    // url = url + "&speech_rate=" + 0;
    // pitch_rate: Optional. The speech pitch. Range: -500–500. Default: 0.
    // url = url + "&pitch_rate=" + 0;
    /**
     * Set the HTTPS GET request.
     * The `encoding` parameter must be set to null to receive the response body as a binary Buffer.
     */
    var options = {
        url: url,
        method: 'GET',
        encoding: null
    };
    request(options, function (error, response, body) {
        /**
         * Process the server response.
         */
        if (error != null) {
            console.log(error);
        }
        else {
            var contentType = response.headers['content-type'];
            if (contentType === undefined || contentType != 'audio/mpeg') {
                console.log('The GET request failed!');
            }
            else {
                fs.writeFileSync(audioSaveFile, body);
                console.log('The GET request succeeded!');
            }
        }
    });
}
function processPOSTRequest(appkeyValue, tokenValue, textValue, audioSaveFile, formatValue, sampleRateValue) {
    var url = 'https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts';
    /**
     * Set the request parameters as a JSON string in the POST request body.
    */
    var task = {
        appkey : appkeyValue,
        token : tokenValue,
        text : textValue,
        format : formatValue,
        sample_rate : sampleRateValue
        // voice: Optional. The synthesis voice. Default: xiaoyun.
        // voice : 'xiaoyun',
        // volume: Optional. The audio volume. Range: 0–100. Default: 50.
        // volume : 50,
        // speech_rate: Optional. The speech rate. Range: -500–500. Default: 0.
        // speech_rate : 0,
        // pitch_rate: Optional. The speech pitch. Range: -500–500. Default: 0.
        // pitch_rate : 0
    };
    var bodyContent = JSON.stringify(task);
    /**
     * Set the POST request headers.
     */
    var httpHeaders = {
        'Content-type' : 'application/json'
    }
    /**
     * Set the HTTPS POST request.
     * The `encoding` parameter must be set to null to receive the response body as a binary Buffer.
     */
    var options = {
        url: url,
        method: 'POST',
        headers: httpHeaders,
        body: bodyContent,
        encoding: null
    };
    request(options, function (error, response, body) {
        /**
         * Process the server response.
         */
        if (error != null) {
            console.log(error);
        }
        else {
            var contentType = response.headers['content-type'];
            if (contentType === undefined || contentType != 'audio/mpeg') {
                console.log('The POST request failed!');
            }
            else {
                fs.writeFileSync(audioSaveFile, body);
                console.log('The POST request succeeded!');
            }
        }
    });
}
var appkey = 'Your AppKey';
var token = 'Your Token';
var text = 'Today is Monday, and the weather is nice.';
var textUrlEncode = encodeURIComponent(text)
                    .replace(/[!'()*]/g, function(c) {
                        return '%' + c.charCodeAt(0).toString(16);
                    });
console.log(textUrlEncode);
var audioSaveFile = 'syAudio.wav';
var format = 'wav';
// The sample rate of the synthesized audio, in Hz.
var sampleRate = 16000;
processGETRequest(appkey, token, textUrlEncode, audioSaveFile, format, sampleRate);
// processPOSTRequest(appkey, token, text, audioSaveFile, format, sampleRate);

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.IO;
using System.Net.Http;
using System.Web;
using Newtonsoft.Json.Linq;
namespace RESTfulAPI
{
    class SpeechSynthesizerRESTfulDemo
    {
        private string appkey;
        private string token;
        public SpeechSynthesizerRESTfulDemo(string appkey, string token)
        {
            this.appkey = appkey;
            this.token = token;
        }
        public void processGETRequest(string text, string audioSaveFile, string format, int sampleRate)
        {
            /**
             * Configure the HTTPS GET request.
             * 1. Use the HTTPS protocol.
             * 2. Domain name of the Speech Synthesis service: nls-gateway-ap-southeast-1.aliyuncs.com
             * 3. Request path of the Speech Synthesis API: /stream/v1/tts
             * 4. Set the parameters used in this example: appkey, token, text, format, and sample_rate.
             * 5. Set the optional request parameters: voice, volume, speech_rate, and pitch_rate.
             */
            string url = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts";
            url = url + "?appkey=" + appkey;
            url = url + "&token=" + token;
            url = url + "&text=" + text;
            url = url + "&format=" + format;
            url = url + "&sample_rate=" + sampleRate.ToString();
            // voice: The voice. Optional. Default value: xiaoyun.
            // url = url + "&voice=" + "xiaoyun";
            // volume: The volume. Value range: 0 to 100. Optional. Default value: 50.
            // url = url + "&volume=" + 50;
            // speech_rate: The speech rate. Value range: -500 to 500. Optional. Default value: 0.
            // url = url + "&speech_rate=" + 0;
            // pitch_rate: The pitch rate. Value range: -500 to 500. Optional. Default value: 0.
            // url = url + "&pitch_rate=" + 0;
            /**
             * Send the HTTPS GET request and process the response from the server.
             */
            HttpClient client = new HttpClient();
            HttpResponseMessage response = null;
            response = client.GetAsync(url).Result;
            string contentType = null;
            if (response.IsSuccessStatusCode)
            {
                string[] typesArray = response.Content.Headers.GetValues("Content-Type").ToArray();
                if (typesArray.Length > 0)
                {
                    contentType = typesArray.First();
                }
            }
            if ("audio/mpeg".Equals(contentType))
            {
                byte[] audioBuff = response.Content.ReadAsByteArrayAsync().Result;
                FileStream fs = new FileStream(audioSaveFile, FileMode.Create);
                fs.Write(audioBuff, 0, audioBuff.Length);
                fs.Flush();
                fs.Close();
                System.Console.WriteLine("The GET request succeed!");
            }
            else
            {
                // The ContentType is null or "application/json".
                System.Console.WriteLine("Response status code and reason phrase: " +
                    response.StatusCode + " " + response.ReasonPhrase);
                string responseBodyAsText = response.Content.ReadAsStringAsync().Result;
                System.Console.WriteLine("The GET request failed: " + responseBodyAsText);
            }
        }
        public void processPOSTRequest(string text, string audioSaveFile, string format, int sampleRate)
        {
            /**
             * Configure the HTTPS POST request.
             * 1. Use the HTTPS protocol.
             * 2. Domain name of the Speech Synthesis service: nls-gateway-ap-southeast-1.aliyuncs.com
             * 3. Request path of the Speech Synthesis API: /stream/v1/tts
             * 4. Set the parameters used in this example: appkey, token, text, format, and sample_rate.
             * 5. Set the optional request parameters: voice, volume, speech_rate, and pitch_rate.
             */
            string url = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts";
            JObject obj = new JObject();
            obj["appkey"] = appkey;
            obj["token"] = token;
            obj["text"] = text;
            obj["format"] = format;
            obj["sample_rate"] = sampleRate;
            // voice: The voice. Optional. Default value: xiaoyun.
            // obj["voice"] = "xiaoyun";
            // volume: The volume. Value range: 0 to 100. Optional. Default value: 50.
            // obj["volume"] = 50;
            // speech_rate: The speech rate. Value range: -500 to 500. Optional. Default value: 0.
            // obj["speech_rate"] = 0;
            // pitch_rate: The pitch rate. Value range: -500 to 500. Optional. Default value: 0.
            // obj["pitch_rate"] = 0;
            String bodyContent = obj.ToString();
            StringContent content = new StringContent(bodyContent, Encoding.UTF8, "application/json");
            /**
             * Send the HTTPS POST request and process the response from the server.
             */
            HttpClient client = new HttpClient();
            HttpResponseMessage response = client.PostAsync(url, content).Result;
            string contentType = null;
            if (response.IsSuccessStatusCode)
            {
                string[] typesArray = response.Content.Headers.GetValues("Content-Type").ToArray();
                if (typesArray.Length > 0)
                {
                    contentType = typesArray.First();
                }
            }
            if ("audio/mpeg".Equals(contentType))
            {
                byte[] audioBuff = response.Content.ReadAsByteArrayAsync().Result;
                FileStream fs = new FileStream(audioSaveFile, FileMode.Create);
                fs.Write(audioBuff, 0, audioBuff.Length);
                fs.Flush();
                fs.Close();
                System.Console.WriteLine("The POST request succeed!");
            }
            else
            {
                System.Console.WriteLine("Response status code and reason phrase: " +
                    response.StatusCode + " " + response.ReasonPhrase);
                string responseBodyAsText = response.Content.ReadAsStringAsync().Result;
                System.Console.WriteLine("The POST request failed: " + responseBodyAsText);
            }
        }
        static void Main(string[] args)
        {
            if (args.Length < 2)
            {
                System.Console.WriteLine("SpeechSynthesizerRESTfulDemo requires the following parameters: <token> <app-key>");
                return;
            }
            string token = args[0];
            string appkey = args[1];
            SpeechSynthesizerRESTfulDemo demo = new SpeechSynthesizerRESTfulDemo(appkey, token);
            string text = "Today is Monday, and the weather is nice.";
            // URL-encode the text based on RFC 3986.
            string textUrlEncode = text;
            textUrlEncode = HttpUtility.UrlEncode(textUrlEncode, Encoding.UTF8)
                .Replace("+", "%20")
                .Replace("*", "%2A")
                .Replace("%7E", "~");
            System.Console.WriteLine(textUrlEncode);
            string audioSaveFile = "syAudio.wav";
            string format = "wav";
            int sampleRate = 16000;
            demo.processGETRequest(textUrlEncode, audioSaveFile, format, sampleRate);
            //demo.processPOSTRequest(text, audioSaveFile, format, sampleRate);
        }
    }
}

package main
import (
    "fmt"
    "net/url"
    "net/http"
    "io/ioutil"
    "encoding/json"
    "strconv"
    "os"
    "bytes"
    "strings"
)
func processGETRequest(appkey string, token string, text string, audioSaveFile string, format string, sampleRate int) {
    /**
     * Configure the HTTPS GET request.
     * 1. Protocol: HTTPS
     * 2. Endpoint: nls-gateway-ap-southeast-1.aliyuncs.com
     * 3. Request path: /stream/v1/tts
     * 4. Parameters used in this example: appkey, token, text, format, and sample_rate.
     * 5. Optional parameters: voice, volume, speech_rate, and pitch_rate.
     */
    var url string = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts"
    url = url + "?appkey=" + appkey
    url = url + "&token=" + token
    url = url + "&text=" + text
    url = url + "&format=" + format
    url = url + "&sample_rate=" + strconv.Itoa(sampleRate)
    // voice: The synthesis voice. Optional. Default: xiaoyun.
    // url = url + "&voice=" + "xiaoyun"
    // volume: The audio volume. Optional. Valid range: 0 to 100. Default: 50.
    // url = url + "&volume=" + strconv.Itoa(50)
    // speech_rate: The speech rate. Optional. Valid range: -500 to 500. Default: 0.
    // url = url + "&speech_rate=" + strconv.Itoa(0)
    // pitch_rate: The pitch rate. Optional. Valid range: -500 to 500. Default: 0.
    // url = url + "&pitch_rate=" + strconv.Itoa(0)
    /**
     * Send the GET request and process the server response.
     */
    response, err := http.Get(url)
    if err != nil {
        fmt.Println("The GET request failed!")
        panic(err)
    }
    defer response.Body.Close()    
    contentType := response.Header.Get("Content-Type")
    body, _ := ioutil.ReadAll(response.Body)
    if ("audio/mpeg" == contentType) {
        file, _ := os.Create(audioSaveFile)
        defer file.Close()
        file.Write([]byte(body))
        fmt.Println("The GET request succeeded!")
    } else {
        // A null or "application/json" Content-Type indicates a failed request.
        statusCode := response.StatusCode
        fmt.Println("HTTP status code: " + strconv.Itoa(statusCode))
        fmt.Println("The GET request failed: " + string(body))
    }
}
func processPOSTRequest(appkey string, token string, text string, audioSaveFile string, format string, sampleRate int) {
    /**
     * Configure the HTTPS POST request.
     * 1. Protocol: HTTPS
     * 2. Endpoint: nls-gateway-ap-southeast-1.aliyuncs.com
     * 3. Request path: /stream/v1/tts
     * 4. Parameters used in this example: appkey, token, text, format, and sample_rate.
     * 5. Optional parameters: voice, volume, speech_rate, and pitch_rate.
     */
    var url string = "https://nls-gateway-ap-southeast-1.aliyuncs.com/stream/v1/tts"
    bodyContent := make(map[string]interface{})
    bodyContent["appkey"] = appkey
    bodyContent["text"] = text
    bodyContent["token"] = token
    bodyContent["format"] = format
    bodyContent["sample_rate"] = sampleRate
    // voice: The synthesis voice. Optional. Default: xiaoyun.
    // bodyContent["voice"] = "xiaoyun"
    // volume: The audio volume. Optional. Valid range: 0 to 100. Default: 50.
    // bodyContent["volume"] = 50
    // speech_rate: The speech rate. Optional. Valid range: -500 to 500. Default: 0.
    // bodyContent["speech_rate"] = 0
    // pitch_rate: The pitch rate. Optional. Valid range: -500 to 500. Default: 0.
    // bodyContent["pitch_rate"] = 0
    bodyJson, err := json.Marshal(bodyContent)
    if err != nil {
        panic(nil)
    }
    /**
     * Send the POST request and process the server response.
     */
    response, err := http.Post(url, "application/json;charset=utf-8", bytes.NewBuffer([]byte(bodyJson)))
    if err != nil {
        panic(err)
    }
    defer response.Body.Close()
    contentType := response.Header.Get("Content-Type")
    body, _ := ioutil.ReadAll(response.Body)
    if ("audio/mpeg" == contentType) {
        file, _ := os.Create(audioSaveFile)
        defer file.Close()
        file.Write([]byte(body))
        fmt.Println("The POST request succeeded!")
    } else {
        // A null or "application/json" Content-Type indicates a failed request.
        statusCode := response.StatusCode
        fmt.Println("HTTP status code: " + strconv.Itoa(statusCode))
        fmt.Println("The POST request failed: " + string(body))
    }    
}
func main() {
    var appkey string = "YOUR_APPKEY"
    var token  string = "YOUR_TOKEN"
    var text string = "Today is Monday, and the weather is nice."
    var textUrlEncode = text
    textUrlEncode = url.QueryEscape(textUrlEncode)
    textUrlEncode = strings.Replace(textUrlEncode, "+", "%20", -1)
    textUrlEncode = strings.Replace(textUrlEncode, "*", "%2A", -1)
    textUrlEncode = strings.Replace(textUrlEncode, "%7E", "~", -1)
    fmt.Println(textUrlEncode)
    var audioSaveFile string = "syAudio.wav"
    var format string = "wav"
    var sampleRate int = 16000
    processGETRequest(appkey, token, textUrlEncode, audioSaveFile, format, sampleRate)
    // processPOSTRequest(appkey, token, text, audioSaveFile, format, sampleRate)
}