python调用科大讯飞语音合成API

前言

在调用科大讯飞语音合成接口时，官方文档只有调用API：文本转pcm语音文件的步骤，这里在官方文档的基础上，进行了下一步骤：pcm文档转为wav文件，并语音播放。

1.官方文档

官方文档入口：https://www.xfyun.cn/doc/tts/online_tts/API.html#%E6%8E%A5%E5%8F%A3%E8%A6%81%E6%B1%82

# -*- 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


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):
        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": "raw", "auf": "audio/L16;rate=16000", "vcn": "xiaoyan", "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")
            ws.close()
        if code != 0:
            errMsg = message["message"]
            print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))
        else:

            with open('./demo.pcm', '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('./demo.pcm'):
            os.remove('./demo.pcm')

    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=' ', APISecret=' ',
                       APIKey=' ',
                       Text="这是一个语音合成示例")
    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})

2.功能延伸

完善脚本包含两个类：

1.url生产类，生成调用API必要的url信息，

重要参数为：科大讯飞控制台的APPID, APIKey, APISecret

2.API调用类，进行主体程序的调用

重要参数为：pcm的生成地址，wav的生成地址

ps:网上的一些帖子，会有报错，一般为官网文档里的地址信息没有修改

# -*- 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 pyaudio
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

# url生产类
class Ws_Param(object):
    # 初始化
    def __init__(self, APPID, APIKey, APISecret, Text):
        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": "raw", "auf": "audio/L16;rate=16000", "vcn": "x4_lingfeizhe_emo", "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: " + "tts-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": "tts-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

# API调用类
class Make_Sound():
    # 初始化
    def __init__(self, output_pcm,output_wav):
        self.output_pcm = output_pcm
        self.output_wav = output_wav

    # 收到message
    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.output_pcm, '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,*args):
        print("### closed ###")


    # 收到websocket连接建立的处理
    def on_open(self,ws):
        output_pcm = self.output_pcm
        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(output_pcm):
                os.remove(output_pcm)

        thread.start_new_thread(run, ())


    # pcm转换为wav
    def pcm_2_wav(self):

        with open(self.output_pcm, 'rb') as pcmfile:
            pcmdata = pcmfile.read()
        with wave.open(self.output_wav, 'wb') as wavfile:
            wavfile.setparams((1, 2, 16000, 0, 'NONE', 'NONE'))
            wavfile.writeframes(pcmdata)
        now_time2 = time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime())
        print("转wav结束时间"+str(now_time2))

    # 播放wav文件
    def sound_out(self):
        CHUNK = 1024
        FORMAT = pyaudio.paInt16
        CHANNELS = 1
        RATE = 16000

        wf = wave.open(self.output_wav, 'rb')
        p = pyaudio.PyAudio()
        stream = p.open(format=FORMAT,
                        channels=CHANNELS,
                        rate=RATE,
                        output=True,
                        frames_per_buffer=CHUNK, )

        data = wf.readframes(CHUNK)

        while len(data) > 0:
            stream.write(data)
            data = wf.readframes(CHUNK)

        stream.stop_stream()
        stream.close()

        p.terminate()

if __name__ == "__main__":
    output_pcm = './data/demo.pcm'
    output_wav = './data/demo.wav'
    
    # 测试时候在此处正确填写相关信息即可运行
    wsParam = Ws_Param(APPID='********', APISecret='********',
                       APIKey='********',
                       Text="这是一个语音合成示例")
    websocket.enableTrace(False)
    wsUrl = wsParam.create_url()
    # 这里调用Make_Sound
    ms = Make_Sound(output_pcm,output_wav)
    ws = websocket.WebSocketApp(wsUrl, on_message=ms.on_message, on_error=ms.on_error, on_close=ms.on_close)
    ws.on_open = ms.on_open
    ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})
    
    # 文本转为pcm
    ms.pcm_2_wav()

    # 播放wav文件
    ms.sound_out()
    print('播放完毕')

3.结果展示