python之调用科大讯飞的语音合成

python之调用科大讯飞的语音合成

没注册的话可以在官网注册一下，新人注册的话语音识别这块有赠送的使用次数

科大讯飞

环境

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
wave   
pyaudio  //linux 下 播放pcm用的，转格式之类的，
//也有其他的；如果下载MP3格式的不用下载

windows 直接 pip install xxx 或 pip3 isntall xxx

linux 的话 自行下载pip 或 有python 3.6以及之后的配置一下即可.

我的环境

ubuntu linux 21.04 
python 3.7

代码（看注解即可）

#!/bin/python3
# 语音合成
import websocket
import datetime
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import ssl
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import _thread as thread
import os
from integrationxuF import pcm2wav 
import wave
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 TTS():
    """
    语音合成 TTS :Text To Speech
    """
    # 初始化
    def __init__(self, APPID, APIKey, APISecret, Text,OutFile,wavFile=None):
        self.APPID = APPID
        self.APIKey = APIKey
        self.APISecret = APISecret
        self.Text = Text
        # 公共参数(common)
        self.CommonArgs = {"app_id": self.APPID}
        self.OutFile = OutFile
        self.wavFile = wavFile
        # 业务参数(business)，更多个性化参数可在官网查看
        """
        aue	string => raw：未压缩的pcm    lame：mp3 (当aue=lame时需传参sfl=1)
        auf string => audio/L16;rate=8000：合成8K 的音频     audio/L16;rate=16000：合成16K 的音频
        vcn string =>	发音人，可选值：请到控制台添加试用或购买发音人，添加后即显示发音人参数值	"xiaoyan"
        这里只是部分，详细的可去官网 https://www.xfyun.cn/doc/tts/online_tts/API.html#%E6%8E%A5%E5%8F%A3%E8%B0%83%E7%94%A8%E6%B5%81%E7%A8%8B
        """
        self.BusinessArgs = {"aue": "lame", "sfl":1,"auf": "audio/L16;rate=16000", "vcn": "aisxping",
         "tte": "utf8","auf":"audio/L16;rate=16000"}
        self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-8')), "UTF8")}

 
    # 运行
    def run(self):
        websocket.enableTrace(False)
        wsUrl = self.create_url()
        ws = websocket.WebSocketApp(wsUrl,
         on_message=self.on_message, 
         on_error=self.on_error, 
         on_close=self.on_close)
        ws.on_open = self.on_open
        ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})
        # self.towav()  # 这个是 请求的文件格式 是 pcm;目的是把pcm转为wav格式的；这里我用的mp3 就没必要使用这个了
        print("-"*10,"运行结束","-"*10)

    # pcm2wav
    def towav(self):
        """
        这里是分割pcm的路径，把转换为WAV格式的放到同目录下；可自行指定路径
        """
        if self.wavFile is  None:
            splits = str(self.OutFile).split('/')
            splits.pop(-1)
            splits.append("demo.wav")
            self.wavFile = '/'.join(splits)
        # print("wavFile:",self.wavFile)
        self.pcm2wav(self.OutFile,self.wavFile)
    
    def pcm2wav(self,pcmfile,wavfile,channels=1,rate=16000):
        with open(pcmfile,'rb') as fp:
            pcmdata = fp.read()
        with wave.open(wavfile, 'wb') as wav:
            wav.setnchannels(channels)
            wav.setsampwidth(16 // 8)
            wav.setframerate(rate)
                # 写入
            wav.writeframes(pcmdata)


    # 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(self,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")
                ws.close()
            if code != 0:
                errMsg = message["message"]
                print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))
            else:

                with open(self.OutFile, '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(self,ws, error):
        print("### error:", error)


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

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

        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
    # 那个文本中的两个句号是为了延长一下时间，不加的话最后一个字听不清
    out =  os.getcwd() + '/python/demo.mp3'
    # 下面这些参数 自己到官网获取即可
    tts = TTS(APPID='',
                    APISecret='',
                    APIKey='',
                       Text="下午的一个语音合成示例。。",OutFile=out)
    tts.run()