def hand_pose(model,move_text): #Camera and font initialization cap=cv2.VideoCapture(1) array=[] array1=[] #The main event loop while(cap.isOpened()): move='' _,img=cap.read() gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) ret,th1 = cv2.threshold(gray.copy(),100,255,cv2.THRESH_TOZERO) _,contours,hierarchy = cv2.findContours(th1.copy(),cv2.RETR_EXTERNAL, 2) cnt=ut.getMaxContour(contours,4000) if cnt!=None: gesture,res=ut.getGestureImg(cnt,img,th1,model) cv2.imshow('PredictedGesture',gesture) move=move_text[res] array.append(move) if len(array)==30: array1.append(move) print move if len(array1)>=5: a=''.join(array1) tts.TTS(a) array1=[] array=[] cv2.imshow('Frame',img) k = 0xFF & cv2.waitKey(10) if k == 27: break cap.release() cv2.destroyAllWindows()
random.seed(0) filenm = random.randint(0,100000) filenm="files\\"+str(filenm)+".srt" print filenm fff = open(filenm,'w') fff.write(subs) subs = pysrt.open(filenm) main_audio = GenSilence(1/100000) cntr=0 print len(subs) cntr=0 last=0 for x in subs: audio_file = "files\\"+str(random.randint(101,100000000))+".mp3" if len(x.text)>0: tts.TTS(x.text, audio_file) aud = AudioSegment.from_mp3(audio_file) #print aud.duration_seconds duration = 60*(x.end.minutes-x.start.minutes)+(x.end.seconds-x.start.seconds+1) rate = aud.duration_seconds/duration rate*=2 if rate<0.55 or rate>3: print "f**k u" rate = max(rate,0.55) rate = min(rate,3) #print duration #print rate aud.speedup(playback_speed=rate) #print aud.duration_seconds
import STT import requests from bs4 import BeautifulSoup import tts query = STT.stt() #query = 'Google' print("Serching from Wikipedia for " + query + " .....") url = "https://www.wikipedia.org/wiki/" + query #print("*****************") response = requests.get(url) #print(response) soup = BeautifulSoup(response.text, "html.parser") #print(soup) #print("*****************************************************************") i = 0 for p in soup.find_all("p"): #print("*****") if (i == 2): text = p.get_text() print(text) tts.TTS(text) tts.play() i = i + 1
from datetime import datetime from tkinter import simpledialog from tkinter import messagebox as mbox import tts import sequiturclient import sys import os import platform sequitur_model = "dicts/de_g2p_model-6" todo_wordlist = "todo_wordlist.txt" output_lexicon = "output_lexicon.txt" auto_save = True tts_client = tts.TTS() # you can configure key bindings here. Note that we need different ones for Mac, # as Cmd is standard for commands (instead of CTRL) and the F1-12 keys are buggy in tkinker on a Mac :/ key_bindings_mac = { "backup_btn": ("<Command-b>", "⌘+B"), "change_g2p_textbox": ("<Command-g>", "⌘+G"), "add_and_next": ("<Command-Return>", "⌘+↵"), "number_key": ("<Command-Key-%d>", "⌘+%d"), "play_btn_hotkey": ("<Command-p>", "⌘+P"), "find_btn_hotkey": ("<Command-f>", "⌘+F") } key_bindings_pc = { "backup_btn": ("<Control-b>", "Ctrl+B"),
def processVid(videoURL): subs = getEng.getShitDone(videoURL) print subs random.seed(0) # filenm = random.randint(0,100000) # filenm="files\\"+str(filenm)+".srt" # print filenm # fff = open(filenm,'w') # fff.write(subs) subs = srt.parse(subs) subs = list(subs) print subs[0].content main_audio = GenSilence(1 / 100000) cntr = 0 cntr = 0 last = 0 for x in subs: audio_file = "/files114382.mp3" if len(x.content) > 0: tts.TTS(x.content.encode('utf-8'), audio_file) aud = AudioSegment.from_mp3(audio_file) #print aud.duration_seconds duration = x.end - x.start duration = duration.total_seconds() rate = aud.duration_seconds / duration # rate*=2 # rate*=2 # if rate<0.55 or rate>3: # print "f**k u" # rate = max(rate,0.55) # rate = min(rate,3) #print duration #print rate # aud.speedup(playback_speed=rate) #print aud.duration_seconds # dur2 = aud.duration_seconds*1000 # curr = start.minutes*60+start.sec # curr=curr*1000 # if curr<=last+minGap: # curr=last+minGap+1 gap = 0 # if cntr<len(subs)-2: # gap=(subs[cntr+2].start.minutes-x.end.minutes)*60 + subs[cntr+2].start.seconds-x.end.seconds # print gap startP = x.start startP = startP.total_seconds() gap = startP - last last = x.end last = last.total_seconds() # gap=0 # print x.end.seconds if gap <= 0: main_audio = main_audio + aud else: main_audio = main_audio + GenSilence(gap) + aud cntr = cntr + 1 # main_audio.speedup(playback_speed=1.5) last_sub_time = subs[-1].end dur = last_sub_time.total_seconds() * 1000 print "ls sub time in sec" main_audio = main_audio[:dur] # main_audio.export("/static/"+videoURL+".mp3") main_audio.export("static/34825.mp3")
import tkinter as tk import tts from multiprocessing import Process import keyboard myTTS = tts.TTS(250) class Application(tk.Frame): def __init__(self, master=None): super().__init__(master) self.master = master self.pack() self.create_widgets() def create_widgets(self): self.instruct = tk.Text(self, height=10, width=30) instructions = """Highlight text and press r""" self.instruct.pack(side="top") self.instruct.insert(tk.END,instructions) # self.read = tk.Button(self) # self.read["text"] = "read" # self.read["command"] = lambda:check(self.runTTS()) # self.read.pack(side="top") self.quit = tk.Button(self, text="QUIT", fg="red", command=self.master.destroy) self.quit.pack(side="bottom") def run_TTS(self): myTTS.text_to_speech(myTTS.copy_clipboard()) def run_TTS():