Python add audio to video opencv - python-3.x

I use python cv2 module to join jpg frames into video, but I can't add audio to it. Is it possible to add audio to video in python without ffmpeg?
P.S. Sorry for my poor English

Use ffpyplayer to handle the audio part.
import cv2
import numpy as np
#ffpyplayer for playing audio
from ffpyplayer.player import MediaPlayer
video_path="../L1/images/Godwin.mp4"
def PlayVideo(video_path):
video=cv2.VideoCapture(video_path)
player = MediaPlayer(video_path)
while True:
grabbed, frame=video.read()
audio_frame, val = player.get_frame()
if not grabbed:
print("End of video")
break
if cv2.waitKey(28) & 0xFF == ord("q"):
break
cv2.imshow("Video", frame)
if val != 'eof' and audio_frame is not None:
#audio
img, t = audio_frame
video.release()
cv2.destroyAllWindows()
PlayVideo(video_path)
The sample code will work but you need to play around the cv2.waitKey(28) depending on the speed of your video.

This is how I am reading audio and video frames:
from moviepy.editor import *
from pafy import pafy
if __name__ == '__main__':
video = pafy.new('https://www.youtube.com/watch?v=K_IR90FthXQ')
stream = video.getbest(preftype='mp4')
video = VideoFileClip(stream.url)
audio = video.audio
for t, video_frame in video.iter_frames(with_times=True):
audio_frame = audio.get_frame(t)
print(audio_frame)
print(video_frame)
This code downloads YouTube video and returns raw frames as numpy arrays.
You can pass the file as an argument to the VideoFileClip instead of the URL.

You can use pygame for audio.
You need to initialize pygame.mixer module
And in the loop, add pygame.mixer.music.play()
But for that, you will need to choose audio file as well.
However, I have found better idea! You can use webbrowser module for playing videos (and because it would play on browser, you can hear sounds!)
import webbrowser
webbrowser.open("video.mp4")

import pygame
pygame.mixer.init()
pygame.mixer.music.load(
'c:Your_file')
pygame.mixer.music.play()
while True:
pygame.time.Clock().tick()
#used to show that you can do other stuff while playing audio
print("hi")

Related

No sound in video downloaded from youtube using pytube

I'm able to download the video using "pytube" library but, the downloaded video has no sound in playback!
Here's what I've tried...
"""
Developer: #skywalkerSam
Aim: To download youtube videos...
Date: 12022.07.13.03:00
"""
from pytube import YouTube
yt = YouTube("https://www.youtube.com/watch?v=kJQP7kiw5Fk", use_oauth=True, allow_oauth_cache=True)
def info():
print("\nTitle: ", yt.title)
print("Views: ", yt.views)
# print("Description: \t", yt.description)
print("Thumbnail: ", yt.thumbnail_url)
print('Stream Options: \n', yt.streams.filter().order_by('resolution').desc(), '\n')
def download():
yt.streams.filter(progressive=True)
stream = yt.streams.get_by_itag(399)
print("\nProcessing Your Request, Please Wait...\n")
stream.download(output_path="C:\\Users\\samsk\\Downloads\\Youtube\\")
print("\nDownload Complete :) \n")
if __name__ == "__main__":
try:
info()
download()
except KeyboardInterrupt:
print("\n\n Operation Cancelled By User :( \n")
exit()
except Exception as e:
print("\nError: ", e)
Please help me with this, Thank You...
You must download the audio and video to combine the two
I did it with moviepy:
import moviepy.editor as mpe
vname = "clip.mp4"
aname = "audio.mp3"
# Download video and rename
video = pytube.YouTube(url).streams.filter(subtype='mp4', res="1080p").first().download()
os.rename(video, vname)
# Download audio and rename
audio = pytube.YouTube(url).streams.filter(only_audio=True).first().download()
os.rename(audio, aname)
# Setting the audio to the video
video = mpe.VideoFileClip(vname)
audio = mpe.AudioFileClip(aname)
final = video.set_audio(audio)
# Output result
final.write_videofile("video.mp4")
# Delete video and audio to keep the result
os.remove(vname)
os.remove(aname)
Here's a working script to download videos from youtube, install required modules on your system, and change youtube URLs (if you want) and You're good to go
import moviepy.editor as mpe
import os
import pytube
vname = "clip.mp4"
aname = "audio.mp3"
# Download video and rename
video = pytube.YouTube("https://www.youtube.com/watch?v=kJQP7kiw5Fk").streams.filter(
subtype='mp4', res="1080p").first().download()
os.rename(video, vname)
# Download audio and rename
audio = pytube.YouTube(
"https://www.youtube.com/watch?v=kJQP7kiw5Fk").streams.filter(only_audio=True).first().download()
os.rename(audio, aname)
# Setting the audio to the video
video = mpe.VideoFileClip(vname)
audio = mpe.AudioFileClip(aname)
final = video.set_audio(audio)
# Output result
final.write_videofile("video.mp4")
# Delete video and audio to keep the result
os.remove(vname)
os.remove(aname)
Takes a bit of time to compile audio & video together. So, give it some time...

Python 3.7 text-to-speech only playing one audio file, sometimes no audio at all, using IDLE editor

I am using the IDLE editor and Python 3.7, and I would like to know why my code is not playing multiple audio files (sequentially) and sometimes not playing audio at all:
import re
import wave
import pyaudio
import _thread
import time
class TextToSpeech:
CHUNK = 1024
def __init__(self, words_pron_dict:str = 'cmudict-0.7b.txt'):
self._l = {}
self._load_words(words_pron_dict)
def _load_words(self, words_pron_dict:str):
with open(words_pron_dict, 'r') as file:
for line in file:
if not line.startswith(';;;'):
key, val = line.split(' ',2)
self._l[key] = re.findall(r"[A-Z]+",val)
def get_pronunciation(self, str_input):
list_pron = []
for word in re.findall(r"[\w']+",str_input.upper()):
if word in self._l:
list_pron += self._l[word]
print(list_pron)
delay=0
for pron in list_pron:
_thread.start_new_thread( TextToSpeech._play_audio, (pron,delay,))
delay += 0.145
def _play_audio(sound, delay):
try:
time.sleep(delay)
wf = wave.open("sounds/"+sound+".wav", 'rb')
p = pyaudio.PyAudio()
stream = p.open(format=p.get_format_from_width(wf.getsampwidth()),
channels=wf.getnchannels(),
rate=wf.getframerate(),
output=True)
data = wf.readframes(TextToSpeech.CHUNK)
while data:
stream.write(data)
data = wf.readframes(TextToSpeech.CHUNK)
stream.stop_stream()
stream.close()
p.terminate()
return
except:
pass
if __name__ == '__main__':
tts = TextToSpeech()
while True:
tts.get_pronunciation(input('Enter a word or phrase: '))
I have a list of audio files that will play in a certain order, depending on what word I type in, when running the code. The code has no errors, but when I run it, when I type in a word, it only plays the first audio file needed (Example: When I type in "buy" it requires these two sounds: "b" and "ie" played together), but it only plays the first sound, "b", and sometimes no sound at all.
Why isn't it playing multiple audio files? I know that lots of people have been having this issue, but haven't been able to solve it.
Thank you for your help in advance, it is greatly appreciated :)

Unable to capture image every 5 seconds using OpenCV

I am trying to capture image in every 5 seconds using opencv through my laptop's built-in webcam. I am using time.sleep(5) for the required pause. In every run, the first image seems to be correctly saved but after that rest all the images are being saved as an unsupported format (when i am opening them). Also I am unable to break the loop by pressing 'q'.
Below is my code.
import numpy as np
import cv2
import time
cap = cv2.VideoCapture(0)
framerate = cap.get(5)
x=1
while(True):
# Capture frame-by-frame
ret, frame = cap.read()
cap.release()
# Our operations on the frame come here
filename = 'C:/Users/shjohari/Desktop/Retail_AI/MySection/to_predict/image' + str(int(x)) + ".png"
x=x+1
cv2.imwrite(filename, frame)
time.sleep(5)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# When everything done, release the capture
cap.release()
cv2.destroyAllWindows()
Any help is appreciated.
Just a small change, solved my issue.
I included the below code inside the loop :P
cap = cv2.VideoCapture(0)
framerate = cap.get(5)

Access IP camera with OpenCV

Can't access the video stream. Can any one please help me to get the video stream. I have searched in google for the solution and post another question in stack overflow but unfortunately nothing can't solve the problem.
import cv2
cap = cv2.VideoCapture()
cap.open('http://192.168.4.133:80/videostream.cgi?user=admin&pwd=admin')
while(cap.isOpened()):
ret, frame = cap.read()
cv2.imshow('frame', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
Use code below to access ipcam directly through opencv. Replace the url in VideoCapture with your particular camera rtsp url. The one given generally works for most cameras I've used.
import cv2
cap = cv2.VideoCapture("rtsp://[username]:[pass]#[ip address]/media/video1")
while True:
ret, image = cap.read()
cv2.imshow("Test", image)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cv2.destroyAllWindows()
You can use urllib to read frames from video stream.
import cv2
import urllib
import numpy as np
stream = urllib.urlopen('http://192.168.100.128:5000/video_feed')
bytes = ''
while True:
bytes += stream.read(1024)
a = bytes.find(b'\xff\xd8')
b = bytes.find(b'\xff\xd9')
if a != -1 and b != -1:
jpg = bytes[a:b+2]
bytes = bytes[b+2:]
img = cv2.imdecode(np.fromstring(jpg, dtype=np.uint8), cv2.IMREAD_COLOR)
cv2.imshow('Video', img)
if cv2.waitKey(1) == 27:
exit(0)
Check this out if you want to stream video from webcam of your pc. https://github.com/shehzi-khan/video-streaming
You can use this code to get live video feeds in browser.
for accessing camera other than your laptop's webcam, you can use RTSP link like this
rtsp://admin:12345#192.168.1.1:554/h264/ch1/main/av_stream"
where
username:admin
password:12345
your camera ip address and port
ch1 is first camera on that DVR
replace cv2.VideoCamera(0) with this link like this for your camera
and it will work
camera.py
import cv2
class VideoCamera(object):
def __init__(self):
# Using OpenCV to capture from device 0. If you have trouble capturing
# from a webcam, comment the line below out and use a video file
# instead.
self.video = cv2.VideoCapture(0)
# If you decide to use video.mp4, you must have this file in the folder
# as the main.py.
# self.video = cv2.VideoCapture('video.mp4')
def __del__(self):
self.video.release()
def get_frame(self):
success, image = self.video.read()
# We are using Motion JPEG, but OpenCV defaults to capture raw images,
# so we must encode it into JPEG in order to correctly display the
# video stream.
ret, jpeg = cv2.imencode('.jpg', image)
return jpeg.tobytes()
main.py
from flask import Flask, render_template, Response
from camera import VideoCamera
app = Flask(__name__)
#app.route('/')
def index():
return render_template('index.html')
def gen(camera):
while True:
frame = camera.get_frame()
yield (b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' + frame + b'\r\n\r\n')
#app.route('/video_feed')
def video_feed():
return Response(gen(VideoCamera()),
mimetype='multipart/x-mixed-replace; boundary=frame')
if __name__ == '__main__':
app.run(host='0.0.0.0', debug=True)
then you can follow this blog to increase your FPS of video stream
Thank You. May be, now urlopen is not under utllib. It is under urllib.request.urlopen.I use this code:
import cv2
from urllib.request import urlopen
import numpy as np
stream = urlopen('http://192.168.4.133:80/video_feed')
bytes = ''
while True:
bytes += stream.read(1024)
a = bytes.find(b'\xff\xd8')
b = bytes.find(b'\xff\xd9')
if a != -1 and b != -1:
jpg = bytes[a:b+2]
bytes = bytes[b+2:]
img = cv2.imdecode(np.fromstring(jpg, dtype=np.uint8), cv2.IMREAD_COLOR)
cv2.imshow('Video', img)
if cv2.waitKey(1) == 27:
exit(0)
You can Use RTSP instead of direct video feed.
Every IP Camera have RTSP to Stream Live Video.
So you can use RTSP Link instead of videofeed
If using python 3, you will probably need to use a bytearray instead of a string. (modifying the current top answer)
with urllib.request.urlopen('http://192.168.100.128:5000/video_feed') as stream:
bytes = bytearray()
while True:
bytes += stream.read(1024)
a = bytes.find(b'\xff\xd8')
b = bytes.find(b'\xff\xd9')
if a != -1 and b != -1:
jpg = bytes[a:b+2]
bytes = bytes[b+2:]
img = cv2.imdecode(np.frombuffer(jpg, dtype=np.uint8), cv2.IMREAD_COLOR)
cv2.imshow('Video', img)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cv2.destroyAllWindows()

Pygame sound file just beeping [duplicate]

I tried pygame for playing wav file like this:
import pygame
pygame.init()
pygame.mixer.music.load("mysound.wav")
pygame.mixer.music.play()
pygame.event.wait()
but It change the voice and I don't know why!
I read this link solutions and can't solve my problem with playing wave file!
for this solution I dont know what should I import?
s = Sound()
s.read('sound.wav')
s.play()
and for this solution /dev/dsp dosen't exist in new version of linux :
from wave import open as waveOpen
from ossaudiodev import open as ossOpen
s = waveOpen('tada.wav','rb')
(nc,sw,fr,nf,comptype, compname) = s.getparams( )
dsp = ossOpen('/dev/dsp','w')
try:
from ossaudiodev import AFMT_S16_NE
except ImportError:
if byteorder == "little":
AFMT_S16_NE = ossaudiodev.AFMT_S16_LE
else:
AFMT_S16_NE = ossaudiodev.AFMT_S16_BE
dsp.setparameters(AFMT_S16_NE, nc, fr)
data = s.readframes(nf)
s.close()
dsp.write(data)
dsp.close()
and when I tried pyglet It give me this error:
import pyglet
music = pyglet.resource.media('mysound.wav')
music.play()
pyglet.app.run()
--------------------------
nima#ca005 Desktop]$ python play.py
Traceback (most recent call last):
File "play.py", line 4, in <module>
music = pyglet.resource.media('mysound.wav')
File "/usr/lib/python2.7/site-packages/pyglet/resource.py", line 587, in media
return media.load(path, streaming=streaming)
File "/usr/lib/python2.7/site-packages/pyglet/media/__init__.py", line 1386, in load
source = _source_class(filename, file)
File "/usr/lib/python2.7/site-packages/pyglet/media/riff.py", line 194, in __init__
format = wave_form.get_format_chunk()
File "/usr/lib/python2.7/site-packages/pyglet/media/riff.py", line 174, in get_format_chunk
for chunk in self.get_chunks():
File "/usr/lib/python2.7/site-packages/pyglet/media/riff.py", line 110, in get_chunks
chunk = cls(self.file, name, length, offset)
File "/usr/lib/python2.7/site-packages/pyglet/media/riff.py", line 155, in __init__
raise RIFFFormatException('Size of format chunk is incorrect.')
pyglet.media.riff.RIFFFormatException: Size of format chunk is incorrect.
AL lib: ReleaseALC: 1 device not closed
You can use PyAudio. An example here on my Linux it works:
#!usr/bin/env python
#coding=utf-8
import pyaudio
import wave
#define stream chunk
chunk = 1024
#open a wav format music
f = wave.open(r"/usr/share/sounds/alsa/Rear_Center.wav","rb")
#instantiate PyAudio
p = pyaudio.PyAudio()
#open stream
stream = p.open(format = p.get_format_from_width(f.getsampwidth()),
channels = f.getnchannels(),
rate = f.getframerate(),
output = True)
#read data
data = f.readframes(chunk)
#play stream
while data:
stream.write(data)
data = f.readframes(chunk)
#stop stream
stream.stop_stream()
stream.close()
#close PyAudio
p.terminate()
Works for me on Windows:
https://pypi.org/project/playsound/
>>> from playsound import playsound
>>> playsound('/path/to/a/sound/file/you/want/to/play.wav')
NOTE: This has a bug in Windows where it doesn't close the stream.
I've added a PR for a fix here:
https://github.com/TaylorSMarks/playsound/pull/53/commits/53240d970aef483b38fc6d364a0ae0ad6f8bf9a0
The reason pygame changes your audio is mixer defaults to a 22k sample rate:
initialize the mixer module
pygame.mixer.init(frequency=22050, size=-16, channels=2, buffer=4096): return None
Your wav is probably 8k. So when pygame plays it, it plays roughly twice as fast. So specify your wav frequency in the init.
Pyglet has some problems correctly reading RIFF headers. If you have a very basic wav file (with exactly a 16 byte fmt block) with no other information in the fmt chunk (like 'fact' data), it works. But it makes no provision for additional data in the chunks, so it's really not adhering to the RIFF interface specification.
PyGame has 2 different modules for playing sound and music, the pygame.mixer module and the pygame.mixer.music module. This module contains classes for loading Sound objects and controlling playback. The difference is explained in the documentation:
The difference between the music playback and regular Sound playback is that the music is streamed, and never actually loaded all at once. The mixer system only supports a single music stream at once.
If you want to play a single wav file, you have to initialize the module and create a pygame.mixer.Sound() object from the file. Invoke play() to start playing the file. Finally, you have to wait for the file to play.
Use get_length() to get the length of the sound in seconds and wait for the sound to finish:
(The argument to pygame.time.wait() is in milliseconds)
import pygame
pygame.mixer.init()
my_sound = pygame.mixer.Sound('mysound.wav')
my_sound.play()
pygame.time.wait(int(my_sound.get_length() * 1000))
Alternatively you can use pygame.mixer.get_busy to test if a sound is being mixed. Query the status of the mixer continuously in a loop:
import pygame
pygame.init()
pygame.mixer.init()
my_sound = pygame.mixer.Sound('mysound.wav')
my_sound.play()
while pygame.mixer.get_busy():
pygame.time.delay(10)
pygame.event.poll()
Windows
winsound
If you are a Windows user,the easiest way is to use winsound.You don't even need to install it.
Not recommended, too few functions
import winsound
winsound.PlaySound("Wet Hands.wav", winsound.SND_FILENAME)
# add winsound.SND_ASYNC flag if you want to wait for it.
# like winsound.PlaySound("Wet Hands.wav", winsound.SND_FILENAME | winsound.SND_ASYNC)
mp3play
If you are looking for more advanced functions, you can try mp3play.
Unluckily,mp3play is only available in Python2 and Windows.
If you want to use it on other platforms,use playsound despite its poor functions.If you want to use it in Python3,I will give you the modified version which is available on Python 3.(at the bottom of the answer)
Also,mp3play is really good at playing wave files, and it gives you more choices.
import time
import mp3play
music = mp3play.load("Wet Hands.wav")
music.play()
time.sleep(music.seconds())
Cross-platform
playsound
Playsound is very easy to use,but it is not recommended because you can't pause or get some infomation of the music, and errors often occurs.Unless other ways doesn't work at all, you may try this.
import playsound
playsound.playsound("Wet Hands.wav", block=True)
pygame
I'm using this code and it works on Ubuntu 22.04 after my test.
If it doesn't work on your machine, consider updating your pygame lib.
import pygame
pygame.mixer.init()
pygame.mixer.music.load("Wet Hands.wav")
pygame.mixer.music.play()
while pygame.mixer.music.get_busy():
pass
pyglet
This works on Windows but it doesn't work on my Ubuntu, so I can do nothing.
import pyglet
import time
sound = pyglet.media.load("Wet Hands.wav", "Wet Hands.wav")
sound.play()
time.sleep(sound.duration)
Conclusion
It seems that you are using Linux,so playsound may be your choice.My code maybe cannot solve your problem by using pygame and pyglet,because I always use Windows.If none of the solutions work on your machine,I suggest you run the program on Windows...
To other users seeing my answer, I have done many tests among many libraries,so if you are using Windows,you may try mp3play which can play both mp3 and wave files, and mp3play is the most pythonic, easy, light-weight and functional library.
mp3play in Python3
just copy the code below and create a file named mp3play.py in your working directory and paste the content.
import random
from ctypes import windll, c_buffer
class _mci:
def __init__(self):
self.w32mci = windll.winmm.mciSendStringA
self.w32mcierror = windll.winmm.mciGetErrorStringA
def send(self, command):
buffer = c_buffer(255)
command = command.encode(encoding="utf-8")
errorcode = self.w32mci(command, buffer, 254, 0)
if errorcode:
return errorcode, self.get_error(errorcode)
else:
return errorcode, buffer.value
def get_error(self, error):
error = int(error)
buffer = c_buffer(255)
self.w32mcierror(error, buffer, 254)
return buffer.value
def directsend(self, txt):
(err, buf) = self.send(txt)
# if err != 0:
# print('Error %s for "%s": %s' % (str(err), txt, buf))
return err, buf
class _AudioClip(object):
def __init__(self, filename):
filename = filename.replace('/', '\\')
self.filename = filename
self._alias = 'mp3_%s' % str(random.random())
self._mci = _mci()
self._mci.directsend(r'open "%s" alias %s' % (filename, self._alias))
self._mci.directsend('set %s time format milliseconds' % self._alias)
err, buf = self._mci.directsend('status %s length' % self._alias)
self._length_ms = int(buf)
def volume(self, level):
"""Sets the volume between 0 and 100."""
self._mci.directsend('setaudio %s volume to %d' %
(self._alias, level * 10))
def play(self, start_ms=None, end_ms=None):
start_ms = 0 if not start_ms else start_ms
end_ms = self.milliseconds() if not end_ms else end_ms
err, buf = self._mci.directsend('play %s from %d to %d'
% (self._alias, start_ms, end_ms))
def isplaying(self):
return self._mode() == 'playing'
def _mode(self):
err, buf = self._mci.directsend('status %s mode' % self._alias)
return buf
def pause(self):
self._mci.directsend('pause %s' % self._alias)
def unpause(self):
self._mci.directsend('resume %s' % self._alias)
def ispaused(self):
return self._mode() == 'paused'
def stop(self):
self._mci.directsend('stop %s' % self._alias)
self._mci.directsend('seek %s to start' % self._alias)
def milliseconds(self):
return self._length_ms
def __del__(self):
self._mci.directsend('close %s' % self._alias)
_PlatformSpecificAudioClip = _AudioClip
class AudioClip(object):
__slots__ = ['_clip']
def __init__(self, filename):
self._clip = _PlatformSpecificAudioClip(filename)
def play(self, start_ms=None, end_ms=None):
if end_ms is not None and end_ms < start_ms:
return
else:
return self._clip.play(start_ms, end_ms)
def volume(self, level):
assert 0 <= level <= 100
return self._clip.volume(level)
def isplaying(self):
return self._clip.isplaying()
def pause(self):
return self._clip.pause()
def unpause(self):
return self._clip.unpause()
def ispaused(self):
return self._clip.ispaused()
def stop(self):
return self._clip.stop()
def seconds(self):
return int(round(float(self.milliseconds()) / 1000))
def milliseconds(self):
return self._clip.milliseconds()
def load(filename):
"""Return an AudioClip for the given filename."""
return AudioClip(filename)

Resources