温馨提示×

温馨提示×

您好,登录后才能下订单哦!

密码登录×
登录注册×
其他方式登录
点击 登录注册 即表示同意《亿速云用户服务条款》

Python 音频生成器

发布时间:2020-07-03 07:55:37 来源:网络 阅读:426 作者:nineteens 栏目:编程语言

  使用Python生成不同声音的音频

  第一步先去百度AI中注册账号,在控制台中创建语音技术应用,获取AppID,API Key,Secret Key

  第二步 引用

  from tkinter import *

  from tkinter.filedialog import askdirectory

  from aip import AipSpeech

  from tkinter import ttk

  第三步搭建窗体

  root = Tk()

  root.title('生成语音')

  path = StringVar()

  pathmc=StringVar()

  pathnr=StringVar()

  Label(root,text = "保存路径:").grid(row = 0, column = 0)

  Entry(root, textvariable = path).grid(row = 0, column = 1)

  Button(root, text = "路径选择", command = selectPath).grid(row = 0, column = 3)

  Label(root,text = "语音名称:").grid(row = 2, column = 0)

  Entry(root, textvariable = pathmc).grid(row = 2, column = 1)

  Label(root,text = "语音内容:").grid(row = 3, column = 0)

  Entry(root, textvariable = pathnr).grid(row = 3, column = 1)

  Button(root, text = "保存", command = Save).grid(row = 4, column = 0)

  #下拉框

  Label(root,text = "声音类型:").grid(row =1, column = 0)

  number = StringVar()

  numberChosen = ttk.Combobox(root, width=12, textvariable=number)

  numberChosen['values'] = ('女声', '男声', '度逍遥', '度丫丫')

  numberChosen.grid(column=1, row=1)

  numberChosen.current(0)

  root.mainloop()

  第四步 创建方法

  #保存地址

  def selectPath():

  path_ = askdirectory()

  path.set(path_)

  print(path_)

  生成音频的参数

  def Save():

  switch = {'女声': 0,

  '男声': 1,

  '度逍遥': 3,

  '度丫丫': 4,

  }

  lx=switch.get(number.get(),"0")

  yuying(path.get(),pathmc.get(),pathnr.get(),lx)

  #生成音频

  def yuying(url,title,contain,lx):

  APP_ID = 'XXX'#百度AI中获得

  API_KEY = 'XXX'

  SECRET_KEY = 'XXX'

  client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

  result = client.synthesis(contain, 'zh', 1, {

  'vol': 5,'per':lx,'spd':2,# per 发音人选择, 0为女声,1为男声,3为情感合成-度逍遥,4为情感合成-度丫丫,默认为普通女 否

  })郑州妇科医院 http://www.zzkdfk120.com/

  if not isinstance(result, dict):

  with open(url+'\\'+title+'.mp3', 'wb') as f:

  f.write(result)

  合起来的代码就是

  from tkinter import *

  from tkinter.filedialog import askdirectory

  from aip import AipSpeech

  from tkinter import ttk

  def selectPath():

  path_ = askdirectory()

  path.set(path_)

  print(path_)

  def Save():

  switch = {'女声': 0,

  '男声': 1,

  '度逍遥': 3,

  '度丫丫': 4,

  }

  lx=switch.get(number.get(),"0")

  yuying(path.get(),pathmc.get(),pathnr.get(),lx)

  def yuying(url,title,contain,lx):

  APP_ID = 'XXX'#百度AI中获得

  API_KEY = 'XXX'

  SECRET_KEY = 'XXX'

  client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

  result = client.synthesis(contain, 'zh', 1, {

  'vol': 5,'per':lx,'spd':2,# per 发音人选择, 0为女声,1为男声,3为情感合成-度逍遥,4为情感合成-度丫丫,默认为普通女 否

  })

  if not isinstance(result, dict):

  with open(url+'\\'+title+'.mp3', 'wb') as f:

  f.write(result)

  root = Tk()

  root.title('生成语音')

  path = StringVar()

  pathmc=StringVar()

  pathnr=StringVar()

  Label(root,text = "保存路径:").grid(row = 0, column = 0)

  Entry(root, textvariable = path).grid(row = 0, column = 1)

  Button(root, text = "路径选择", command = selectPath).grid(row = 0, column = 3)

  Label(root,text = "语音名称:").grid(row = 2, column = 0)

  Entry(root, textvariable = pathmc).grid(row = 2, column = 1)

  Label(root,text = "语音内容:").grid(row = 3, column = 0)

  Entry(root, textvariable = pathnr).grid(row = 3, column = 1)

  Button(root, text = "保存", command = Save).grid(row = 4, column = 0)

  Label(root,text = "声音类型:").grid(row =1, column = 0)

  number = StringVar()

  numberChosen = ttk.Combobox(root, width=12, textvariable=number)

  numberChosen['values'] = ('女声', '男声', '度逍遥', '度丫丫')

  numberChosen.grid(column=1, row=1)

  numberChosen.current(0)

  root.mainloop()

  效果图

  

Python 音频生成器


向AI问一下细节

免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。

AI