笔者花费半天时间搭建的网站:https://tool.szfx.top/tts

一、功能介绍

讯飞在线语音合成将文字转化为自然流畅的人声,提供100+发音人供您选择,支持多语种、多方言和中英混合,可灵活配置音频参数。广泛应用于新闻阅读、出行导航、智能硬件和通知播报等场景。

二、搭建教程

前期准备工作请参考文章:

讯飞星火大模型API矩阵 讯飞星火大模型API矩阵 笔者试用后感觉还不错,遂推荐给大家,以飨开发者 讯飞开放平台涵盖内容: 星火认知大模型、语音识别、语音合成、语音扩展、自然语言处理、文字识别、图像识别等。 免费注册账号并认证:https://xing... 时间:2024/5/10 分类:网络技术 阅读:97

官方提供的demo有python3、java、nodejs、js语言,这里以PHP调用为例构建一个API

index.php获取待转换文本和发音人,将参数传到python处理,将生成的cache.mp3文件重命名复制到时间线文件夹内。

<?php
header('Access-Control-Allow-Origin:*');
header('Content-type: application/json');

$text=isset($_GET['text'])? $_GET['text'] :null; 
if(empty($text)){die("请传入文本参数");}
$vcn=isset($_GET['vcn'])? $_GET['vcn'] :null; 
if(empty($vcn)){$vcn= "xiaoyan";}

$str = exec("python3 tts_ws.py $text $vcn");
$res = json_decode($str, true);//转换为数组
$response_msg = $res['message'];
if($response_msg == 'success') {$code = '200';}
else{$code = '202';}

$mp3Name = date("His", time()) . "_" . rand(1000, 9999) . '.mp3';
if (strstr($base64, ",")) {
    $base64 = explode(',', $base64);
    $base64 = $base64[1];
}
$pure_path = date("Ymd", time());
$path = "./data/" .$pure_path;
if (!is_dir($path)) { //判断目录是否存在 不存在就创建
    mkdir($path, 0777, true);
}
$Mp3Src = $path . "/" . $mp3Name; //mp3音频文件名字
copy("./cache.mp3", $Mp3Src);
unlink("./cache.mp3");
$json_return = array(
    "code" => $code,
    "src" => $text,
    "dst" => "https://api.szfx.top/xftts/data/".$pure_path. "/" . $mp3Name
);
echo json_encode($json_return, JSON_UNESCAPED_UNICODE);

tts_ws.py文件内写入内容:

# -*- coding:utf-8 -*-
#
#   author: iflytek
#
#  本demo测试时运行的环境为:Windows + Python3.7
#  本demo测试成功运行时所安装的第三方库及其版本如下:
#   cffi==1.12.3
#   gevent==1.4.0
#   greenlet==0.4.15
#   pycparser==2.19
#   six==1.12.0
#   websocket==0.2.1
#   websocket-client==0.56.0
#   合成小语种需要传输小语种文本、使用小语种发音人vcn、tte=unicode以及修改文本编码方式
#  错误码链接:https://www.xfyun.cn/document/error-code (code返回错误码时必看)
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
import websocket
import datetime
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import time
import ssl
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import _thread as thread
import os
import sys

STATUS_FIRST_FRAME = 0  # 第一帧的标识
STATUS_CONTINUE_FRAME = 1  # 中间帧标识
STATUS_LAST_FRAME = 2  # 最后一帧的标识


class Ws_Param(object):
    # 初始化
    def __init__(self, APPID, APIKey, APISecret, Text, Vcn):
        self.APPID = APPID
        self.APIKey = APIKey
        self.APISecret = APISecret
        self.Text = Text

        # 公共参数(common)
        self.CommonArgs = {"app_id": self.APPID}
        # 业务参数(business),更多个性化参数可在官网查看
        self.BusinessArgs = {"aue": "lame","sfl": 1, "auf": "audio/L16;rate=16000", "vcn": Vcn, "tte": "utf8"}
        self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-8')), "UTF8")}
        #使用小语种须使用以下方式,此处的unicode指的是 utf16小端的编码方式,即"UTF-16LE"”
        #self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-16')), "UTF8")}

    # 生成url
    def create_url(self):
        url = 'wss://tts-api.xfyun.cn/v2/tts'
        # 生成RFC1123格式的时间戳
        now = datetime.now()
        date = format_date_time(mktime(now.timetuple()))

        # 拼接字符串
        signature_origin = "host: " + "ws-api.xfyun.cn" + "\n"
        signature_origin += "date: " + date + "\n"
        signature_origin += "GET " + "/v2/tts " + "HTTP/1.1"
        # 进行hmac-sha256进行加密
        signature_sha = hmac.new(self.APISecret.encode('utf-8'), signature_origin.encode('utf-8'),
                                 digestmod=hashlib.sha256).digest()
        signature_sha = base64.b64encode(signature_sha).decode(encoding='utf-8')

        authorization_origin = "api_key=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"" % (
            self.APIKey, "hmac-sha256", "host date request-line", signature_sha)
        authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')
        # 将请求的鉴权参数组合为字典
        v = {
            "authorization": authorization,
            "date": date,
            "host": "ws-api.xfyun.cn"
        }
        # 拼接鉴权参数,生成url
        url = url + '?' + urlencode(v)
        # print("date: ",date)
        # print("v: ",v)
        # 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释,比对相同参数时生成的url与自己代码生成的url是否一致
        # print('websocket url :', url)
        return url

def on_message(ws, message):
    try:
        message =json.loads(message)
        code = message["code"]
        sid = message["sid"]
        audio = message["data"]["audio"]
        audio = base64.b64decode(audio)
        status = message["data"]["status"]
        # print(message)
        if status == 2:
            # print("ws is closed")
            print(json.dumps(message))
            ws.close()
        if code != 0:
            errMsg = message["message"]
            print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))
        else:

            with open('./cache.mp3', 'ab') as f:
                f.write(audio)

    except Exception as e:
        print("receive msg,but parse exception:", e)



# 收到websocket错误的处理
def on_error(ws, error):
    print("### error:", error)


# 收到websocket关闭的处理
def on_close(ws):
    print("### closed ###")


# 收到websocket连接建立的处理
def on_open(ws):
    def run(*args):
        d = {"common": wsParam.CommonArgs,
             "business": wsParam.BusinessArgs,
             "data": wsParam.Data,
             }
        d = json.dumps(d)
        # print("------>开始发送文本数据")
        ws.send(d)
        if os.path.exists('./cache.mp3'):
            os.remove('./cache.mp3')

    thread.start_new_thread(run, ())


if __name__ == "__main__":
    # 测试时候在此处正确填写相关信息即可运行
    wsParam = Ws_Param(APPID='xxxxxx', APISecret='xxxxxx',
                       APIKey='xxxxxx',
                       Text=sys.argv[1],
                       Vcn=sys.argv[2])
    websocket.enableTrace(False)
    wsUrl = wsParam.create_url()
    ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close)
    ws.on_open = on_open
    ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})

三、调用实例

请求地址:

https://你的api地址/?text=hello,world!&vcn=aisbabyxu

返回数据:

{
    "code": "200",
    "src": "hello,world!",
    "dst": "https://你的api地址/data/20240602/193032_8715.mp3"
}

Demo:https://api.szfx.top/api/xftts.html

Invitation
QQ Group
1095632335

created:04/01/2020

Welcome to the Group

Use this card to join us and participate in a pleasant discussion together .

Welcome to JISHUSONGSHU Group,wish you a nice day .