利用Python打造一個語音合成系統(tǒng)

pip install websocket-clientpip install playsound

class TtsPlay:def __init__(self): #初始化函數(shù)def play_sound(self):#播放音頻函數(shù)def select_vcn(self,*arg):#選擇下拉框設置發(fā)音人def xfyun_tts(self):#進行語音合成

def __init__(self):    self.vcn = 'xiaoyan'    self.APP_ID = 'xxx'# 請?zhí)钌献约旱腶ppid    self.API_KEY = 'xxx'# 請?zhí)钌献约旱腶ppkey????self.SECRET_KEY?=?'xxx'?#?請?zhí)钌献约旱腶ppsecret
    self.fname = ""
    self.root = tk.Tk()  # 初始化窗口    self.root.title("語音合成系統(tǒng)")  # 窗口名稱    self.root.geometry("600x550")  # 設置窗口大小    self.root.resizable(0, 0)   # 為了方便固定窗口大小    self.tk_lb = tk.Label(self.root, text='請選擇語音發(fā)音人')  # 標簽    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    # 設置下拉列表框的內容    self.tk_cb_vcn['values'] = ("甜美女聲-小燕", "親切男聲-許久", "知性女聲-小萍", "可愛童聲-許小寶", "親切女聲-小婧")    self.tk_cb_vcn.current(0)  # 將當前選擇狀態(tài)置為0,也就是第一項    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='進行語音合成', width=10, height=1, command=self.xfyun_tts)  # 按鈕    self.tk_play = tk.Button(self.root, text='播放', width=10, height=1, command=self.play_sound)  # 按鈕    # 各個組件的位置    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):        if self.tk_cb_vcn.get() == '甜美女聲-小燕':            self.vcn = "xiaoyan"        elif self.tk_cb_vcn.get() == '親切男聲-許久':            self.vcn = "aisjiuxu"        elif self.tk_cb_vcn.get() == '知性女聲-小萍':            self.vcn = "aisxping"        elif self.tk_cb_vcn.get() == '可愛童聲-許小寶':            self.vcn = "aisbabyxu"        elif self.tk_cb_vcn.get() == '親切女聲-小婧':            self.vcn = "aisjinger"

# -*- coding:utf-8 -*-##   author: iflytek##  本demo測試時運行的環(huán)境為：Windows + Python3.7#  本demo測試成功運行時所安裝的第三方庫及其版本如下：#   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#   合成小語種需要傳輸小語種文本、使用小語種發(fā)音人vcn、tte=unicode以及修改文本編碼方式#  錯誤碼鏈接：https://www.xfyun.cn/document/error-code （code返回錯誤碼時必看）# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #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
STATUS_FIRST_FRAME = 0  # 第一幀的標識STATUS_CONTINUE_FRAME = 1  # 中間幀標識STATUS_LAST_FRAME?=?2??#?最后一幀的標識
PCM_PATH = "./demo.pcm"

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        # 業(yè)務參數(shù)(business)，更多個性化參數(shù)可在官網查看        self.tts_business_args = {"aue": "raw", "auf": "audio/L16;rate=16000", "vcn": self.tts_vcn, "tte": "utf8"}        # 使用小語種須使用以下方式，此處的unicode指的是 utf16小端的編碼方式，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            # 公共參數(shù)(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格式的時間戳        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"        # 進行hmac-sha256進行加密        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')        # 將請求的鑒權參數(shù)組合為字典        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錯誤的處理def on_error(ws, error):    print("### error:", error)
# 收到websocket關閉的處理def on_close(ws):    print("### closed ###")

# 收到websocket連接建立的處理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("------>開始發(fā)送文本數(shù)據")        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__":    text2wav(appid='xxx',             api_secret='xxx',             api_key='xxx',             text="這是一個測試",             vcn="xiaoyan",             fname="./demo.wav")