Generating audio with different sounds using Python
The first step is to go to Baidu AI to register an account, create a voice technology application in the console, get the AppID, API Key, Secret Key
Step 2 Citation
from tkinter import * from import askdirectory from aip import AipSpeech from tkinter import ttk
Step 3 Build Forms
root = Tk()
('Generate speech')
path = StringVar()
pathmc=StringVar()
pathnr=StringVar()
Label(root,text = "Save Path:").grid(row = 0, column = 0)
Entry(root, textvariable = path).grid(row = 0, column = 1)
Button(root, text = "Path Selection", command = selectPath).grid(row = 0, column = 3)
Label(root,text = "Voice name:").grid(row = 2, column = 0)
Entry(root, textvariable = pathmc).grid(row = 2, column = 1)
Label(root,text = "Voice content:").grid(row = 3, column = 0)
Entry(root, textvariable = pathnr).grid(row = 3, column = 1)
Button(root, text = "Save.", command = Save).grid(row = 4, column = 0)
#DownLoadFrame
Label(root,text = "Sound Type:").grid(row =1, column = 0)
number = StringVar()
numberChosen = (root, width=12, textvariable=number)
numberChosen['values'] = ('Female Voice', 'Male Voice', 'Degree of freedom', 'Do Ya Ya')
(column=1, row=1)
(0)
()
Step 4 Create Methods
# Saved Addresses
def selectPath():
path_ = askdirectory()
(path_)
print(path_)
Parameters for generating audio
def Save():
switch = {'Female Voice': 0,
'Male Voice': 1,
'Degree of freedom': 3,
'Do Ya Ya': 4,
}
lx=((),"0")
yuying((),(),(),lx)
# Generate Audio
def yuying(url,title,contain,lx):
APP_ID = 'XXX'#Baidu AI in Get
API_KEY = 'XXX'
SECRET_KEY = 'XXX'
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
result = (contain, 'zh', 1, {
'vol': 5,'per':lx,'spd':2,# per Pronunciator Selection, 0 for Female, 1 for Male, 3 for Emotionally Synthesized-Do Easy, 4 for Emotionally Synthesized-Do Ya Ya, Default is Normal Female No
})
if not isinstance(result, dict):
with open(url+'\\'+title+'.mp3', 'wb') as f:
(result)
The combined code is
from tkinter import *
from import askdirectory
from aip import AipSpeech
from tkinter import ttk
def selectPath():
path_ = askdirectory()
(path_)
print(path_)
def Save():
switch = {'Female Voice': 0,
'Male Voice': 1,
'Degree of freedom': 3,
'Do Ya Ya': 4,
}
lx=((),"0")
yuying((),(),(),lx)
def yuying(url,title,contain,lx):
APP_ID = 'XXX'#Baidu AI in Get
API_KEY = 'XXX'
SECRET_KEY = 'XXX'
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
result = (contain, 'zh', 1, {
'vol': 5,'per':lx,'spd':2,# per Pronunciator Selection, 0 for Female, 1 for Male, 3 for Emotionally Synthesized-Do Easy, 4 for Emotionally Synthesized-Do Ya Ya, Default is Normal Female No
})
if not isinstance(result, dict):
with open(url+'\\'+title+'.mp3', 'wb') as f:
(result)
root = Tk()
('Generate speech')
path = StringVar()
pathmc=StringVar()
pathnr=StringVar()
Label(root,text = "Save Path:").grid(row = 0, column = 0)
Entry(root, textvariable = path).grid(row = 0, column = 1)
Button(root, text = "Path Selection", command = selectPath).grid(row = 0, column = 3)
Label(root,text = "Voice name:").grid(row = 2, column = 0)
Entry(root, textvariable = pathmc).grid(row = 2, column = 1)
Label(root,text = "Voice content:").grid(row = 3, column = 0)
Entry(root, textvariable = pathnr).grid(row = 3, column = 1)
Button(root, text = "Save.", command = Save).grid(row = 4, column = 0)
Label(root,text = "Sound Type:").grid(row =1, column = 0)
number = StringVar()
numberChosen = (root, width=12, textvariable=number)
numberChosen['values'] = ('Female Voice', 'Male Voice', 'Degree of freedom', 'Do Ya Ya')
(column=1, row=1)
(0)
()
rendering (visual representation of how things will turn out)
This is the whole content of this article.