【NLP】Pyhon+讯飞开放平台:​手把手带你写一个智能语音播报系统

import websocketimport datetimeimport hashlibimport base64import hmacimport jsonfrom urllib.parse import urlencodeimport sslfrom wsgiref.handlers import format_date_timefrom datetime import datetimefrom time import mktimeimport _thread as threadimport osimport wave
import tkinter as tkfrom tkinter import ttk
import timefrom playsound import playsoundimport 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
PCM_PATH = "./demo.pcm"
class TtsPlay:
    def __init__(self):#初始化函数        self.vcn = 'xiaoyan'        self.APP_ID = '自行填入'  # 请填上自己的appid        self.API_KEY = '自行填入'  # 请填上自己的appkey        self.SECRET_KEY = '自行填入'  # 请填上自己的appsecret
        self.fname = ""
        self.root = tk.Tk()  # 初始化窗口        self.root.title("智能语音播报系统")  # 窗口名称        self.root.geometry("600x550")  # 设置窗口大小        self.root.resizable(0, 0)  # 为了方便固定窗口大小        self.tk_lb = tk.Label(self.root, text='请选择语音发音人')  # 标签        self.tk_text = tk.Text(self.root, width=77, height=30)  # 多行文本框        self.tk_cb_vcn = ttk.Combobox(self.root, width=12)  # 下拉列表框
        #设置下拉列表框的内容        self.tk_cb_vcn['values'] = ("甜美女声-小燕", "亲切男声-许久", "知性女声-小萍", "可爱童声-许小宝", "亲切女声-小婧")        self.tk_cb_vcn.current(0)  # 将当前选择状态置为0,也就是第一项        self.tk_cb_vcn.bind("<>", self.select_vcn)        self.tk_tts_file = tk.Label(self.root, text='生成文件名')        self.b1 = tk.Button(self.root, text='开始合成吧', width=10, height=1, command=self.xfyun_tts)  # 按钮        self.tk_play = tk.Button(self.root, text='直接播放吧', width=10, height=1, command=self.play_sound)  # 按钮
        # 各个组件的位置        self.tk_tts_file.place(x=30, y=500)        self.b1.place(x=300, y=500)        self.tk_play.place(x=400, y=500)        self.tk_lb.place(x=30, y=30)        self.tk_cb_vcn.place(x=154, y=30)
        self.tk_text.place(x=30, y=60)        self.root.mainloop()
    def select_vcn(self, *args):#选择下拉框设置发音人        if self.tk_cb_vcn.get() == '甜美女声-小燕':         self.vcn = "xiaoyan"        elif self.tk_cb_vcn.get() == '亲切男声-许久':         self.vcn = "aisjiuxu"        elif self.tk_cb_vcn.get() == '知性女声-小萍':         self.vcn = "aisxping"        elif self.tk_cb_vcn.get() == '可爱童声-许小宝':         self.vcn = "aisbabyxu"        elif self.tk_cb_vcn.get() == '亲切女声-小婧':         self.vcn = "aisjinger"
    def xfyun_tts(self):  # 进行语音合成        tts_text = self.tk_text.get('0.0', 'end')  # 获取文本内容        # 前后的空格以及换行符        tts_text = tts_text.strip('\r\n')        tts_text = tts_text.strip('\n')        tts_text = tts_text.strip(' ')
        if not tts_text:            tk.messagebox.showinfo("提示", "请输入文本内容")            return
        fname = time.strftime("%Y%m%d%H%M%S", time.localtime())        self.fname = os.path.dirname(sys.argv[0]) + "/" + fname + ".wav"
        self.tk_tts_file["text"] = self.fname        text2wav(self.APP_ID, self.SECRET_KEY, self.API_KEY, tts_text, self.vcn, self.fname)
    def play_sound(self):# 播放音频函数        playsound(self.fname)

class Ws_Param(object):    # 初始化    def __init__(self):        self.tts_vcn = ""        self.tts_business_args = ""        self.tts_common_args = ""        self.tts_text_data = ""        self.APPID = ""        self.APIKey = ""        self.APISecret = ""
    def set_tts_params(self, text, vcn):        self.tts_vcn = vcn        # 业务参数(business)，更多个性化参数可在官网查看        self.tts_business_args = {"aue": "raw", "auf": "audio/L16;rate=16000", "vcn": self.tts_vcn, "tte": "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.tts_text_data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-16')), "UTF8")}        self.tts_text_data = {"status": 2, "text": str(base64.b64encode(text.encode('utf-8')), "UTF8")}
    def set_params(self, appid, api_seccret, api_key):        if appid != "":            self.APPID = appid            # 公共参数(common)            self.tts_common_args = {"app_id": self.APPID}
        if api_key != "":            self.APIKey = api_key
        if api_seccret != "":            self.APISecret = api_seccret
    # 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"        }
        url = url + '?' + urlencode(v)
        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(code, sid, status)        if status == 2:            print("ws is closed")            ws.close()        if code != 0:            err_msg = message["message"]            print("sid:%s call error:%s code is:%s" % (sid, err_msg, code))        else:            with open(PCM_PATH, '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.tts_common_args,             "business": wsParam.tts_business_args,             "data": wsParam.tts_text_data,             }        d = json.dumps(d)        print("------>开始发送文本数据")        ws.send(d)        if os.path.exists(PCM_PATH):            os.remove(PCM_PATH)
    thread.start_new_thread(run, ())

def text2wav(appid, api_secret, api_key, text, vcn, fname):    wsParam.set_params(appid, api_secret, api_key)    wsParam.set_tts_params(text, vcn)    websocket.enableTrace(False)    ws_url = wsParam.create_url()    ws = websocket.WebSocketApp(ws_url, 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})
    pcm2wav(PCM_PATH, fname)

def pcm2wav(fname, dstname):    with open(fname, 'rb') as pcmfile:        pcmdata = pcmfile.read()        print(len(pcmdata))    with wave.open(dstname, "wb") as wavfile:        wavfile.setparams((1, 2, 16000, 0, 'NONE', 'NONE'))        wavfile.writeframes(pcmdata)
wsParam = Ws_Param()

# 注意一下需要填入自己的appid、api_secret、api_keyif __name__ == "__main__":
    a=TtsPlay()
    #这个函数可以单独执行获取文件    # text2wav(appid='自行填入',    #          api_secret='自行填入',    #          api_key='自行填入',    #          text="这是一个测试",    #          vcn="xiaoyan",    #          fname="./demo.wav")