Recherche avancée

Sur d’autres sites (9033)

• How to render two videos with alpha channel in real time in pygame with synched audio ?

  21 décembre 2024, par Francesco Calderone

  I need to play two videos with synched sound in real-time with Pygame.
Pygame does not currently support video streams, so I am using a ffmpeg subprocess.
The first video is a prores422_hq. This is a background video with no alpha channel.
The second video is a prores4444 overlay video with an alpha channel, and it needs to be played in real-tim on top of the first video (with transparency).
All of this needs synched sound from the first base video only.

  


  I have tried many libraries, including pymovie pyav and opencv. The best result so far is to use a subprocess with ffmpeg.

  


  ffmpeg -i testing/stefano_prores422_hq.mov -stream_loop -1 -i testing/key_prores4444.mov -filter_complex "[1:v]format=rgba,colorchannelmixer=aa=1.0[overlay];[0:v][overlay]overlay" -f nut pipe:1 | ffplay -

  


  When running this in the terminal and playing with ffplay, everything is perfect, the overlay looks good, no dropped frames, and the sound is in synch.

  


  However, trying to feed that to pygame via a subprocess creates either video delays and drop frames or audio not in synch.

  


  EXAMPLE ONE :

  


  # SOUND IS NOT SYNCHED - sound is played via ffplay
import pygame
import subprocess
import numpy as np
import sys

def main():
    pygame.init()
    screen_width, screen_height = 1920, 1080
    screen = pygame.display.set_mode((screen_width, screen_height))
    pygame.display.set_caption("PyGame + FFmpeg Overlay with Audio")
    clock = pygame.time.Clock()

    # LAUNCH AUDIO-ONLY SUBPROCESS
    audio_cmd = [
        "ffplay",
        "-nodisp",          # no video window
        "-autoexit",        # exit when video ends
        "-loglevel", "quiet",
        "testing/stefano_prores422_hq.mov"
    ]
    audio_process = subprocess.Popen(audio_cmd)

    # LAUNCH VIDEO-OVERLAY SUBPROCESS
    ffmpeg_command = [
        "ffmpeg",
        "-re",                        # read at native frame rate
        "-i", "testing/stefano_prores422_hq.mov",
        "-stream_loop", "-1",         # loop alpha video
        "-i", "testing/key_prores4444.mov",
        "-filter_complex",
        "[1:v]format=rgba,colorchannelmixer=aa=1.0[overlay];"  # ensure alpha channel
        "[0:v][overlay]overlay",      # overlay second input onto first
        "-f", "rawvideo",             # output raw video
        "-pix_fmt", "rgba",           # RGBA format
        "pipe:1"                      # write to STDOUT
    ]
    video_process = subprocess.Popen(
        ffmpeg_command,
        stdout=subprocess.PIPE,
        stderr=subprocess.DEVNULL
    )
    frame_size = screen_width * screen_height * 4  # RGBA = 4 bytes/pixel
    running = True
    while running:
        for event in pygame.event.get():
            if event.type == pygame.QUIT:
                running = False
                break

        raw_frame = video_process.stdout.read(frame_size)

        if len(raw_frame) < frame_size:
            running = False
            break
        # Convert raw bytes -> NumPy array -> PyGame surface
        frame_array = np.frombuffer(raw_frame, dtype=np.uint8)
        frame_array = frame_array.reshape((screen_height, screen_width, 4))
        frame_surface = pygame.image.frombuffer(frame_array.tobytes(), 
                                                (screen_width, screen_height), 
                                                "RGBA")
        screen.blit(frame_surface, (0, 0))
        pygame.display.flip()
        clock.tick(25)
    video_process.terminate()
    video_process.wait()
    audio_process.terminate()
    audio_process.wait()
    pygame.quit()
    sys.exit()

if __name__ == "__main__":
    main()



  


  EXAMPLE TWO

  


  # NO VIDEO OVERLAY - SOUND SYNCHED
import ffmpeg
import pygame
import sys
import numpy as np
import tempfile
import os

def extract_audio(input_file, output_file):
    """Extract audio from video file to temporary WAV file"""
    (
        ffmpeg
        .input(input_file)
        .output(output_file, acodec='pcm_s16le', ac=2, ar='44100')
        .overwrite_output()
        .run(capture_stdout=True, capture_stderr=True)
    )

def get_video_fps(input_file):
    probe = ffmpeg.probe(input_file)
    video_info = next(s for s in probe['streams'] if s['codec_type'] == 'video')
    fps_str = video_info.get('r_frame_rate', '25/1')
    num, den = map(int, fps_str.split('/'))
    return num / den

input_file = "testing/stefano_prores422_hq.mov"

# Create temporary WAV file
temp_audio = tempfile.NamedTemporaryFile(suffix='.wav', delete=False)
temp_audio.close()
extract_audio(input_file, temp_audio.name)

probe = ffmpeg.probe(input_file)
video_info = next(s for s in probe['streams'] if s['codec_type'] == 'video')
width = int(video_info['width'])
height = int(video_info['height'])
fps = get_video_fps(input_file)

process = (
    ffmpeg
    .input(input_file)
    .output('pipe:', format='rawvideo', pix_fmt='rgb24')
    .run_async(pipe_stdout=True)
)

pygame.init()
pygame.mixer.init(frequency=44100, size=-16, channels=2, buffer=4096)
clock = pygame.time.Clock()
screen = pygame.display.set_mode((width, height))

pygame.mixer.music.load(temp_audio.name)
pygame.mixer.music.play()

frame_count = 0
start_time = pygame.time.get_ticks()

while True:
    for event in pygame.event.get():
        if event.type == pygame.QUIT:
            pygame.mixer.music.stop()
            os.unlink(temp_audio.name)
            sys.exit()

    in_bytes = process.stdout.read(width * height * 3)
    if not in_bytes:
        break

    # Calculate timing for synchronization
    expected_frame_time = frame_count * (1000 / fps)
    actual_time = pygame.time.get_ticks() - start_time
    
    if actual_time < expected_frame_time:
        pygame.time.wait(int(expected_frame_time - actual_time))
    
    in_frame = (
        np.frombuffer(in_bytes, dtype="uint8")
        .reshape([height, width, 3])
    )
    out_frame = pygame.surfarray.make_surface(np.transpose(in_frame, (1, 0, 2)))
    screen.blit(out_frame, (0, 0))
    pygame.display.flip()
    
    frame_count += 1

pygame.mixer.music.stop()
process.wait()
pygame.quit()
os.unlink(temp_audio.name)


  


  I also tried using pygame mixer and a separate mp3 audio file, but that didn't work either. Any help on how to synch the sound while keeping the playback of both videos to 25 FPS would be greatly appreciated !!!

  


• How to render two videos with alpha channel in real time in pygame ?

  21 décembre 2024, par Francesco Calderone

  I need to play two videos with synched sound in real-time with Pygame.
Pygame does not currently support video streams, so I am using a ffmpeg subprocess.
The first video is a prores422_hq. This is a background video with no alpha channel.
The second video is a prores4444 overlay video with an alpha channel, and it needs to be played in real-tim on top of the first video (with transparency).
All of this needs synched sound from the first base video only.

  


  I have tried many libraries, including pymovie pyav and opencv. The best result so far is to use a subprocess with ffmpeg.

  


  ffmpeg -i testing/stefano_prores422_hq.mov -stream_loop -1 -i testing/key_prores4444.mov -filter_complex "[1:v]format=rgba,colorchannelmixer=aa=1.0[overlay];[0:v][overlay]overlay" -f nut pipe:1 | ffplay -

  


  When running this in the terminal and playing with ffplay, everything is perfect, the overlay looks good, no dropped frames, and the sound is in synch.

  


  However, trying to feed that to pygame via a subprocess creates either video delays and drop frames or audio not in synch.

  


  EXAMPLE ONE :

  


  # SOUND IS NOT SYNCHED - sound is played via ffplay
import pygame
import subprocess
import numpy as np
import sys

def main():
    pygame.init()
    screen_width, screen_height = 1920, 1080
    screen = pygame.display.set_mode((screen_width, screen_height))
    pygame.display.set_caption("PyGame + FFmpeg Overlay with Audio")
    clock = pygame.time.Clock()

    # LAUNCH AUDIO-ONLY SUBPROCESS
    audio_cmd = [
        "ffplay",
        "-nodisp",          # no video window
        "-autoexit",        # exit when video ends
        "-loglevel", "quiet",
        "testing/stefano_prores422_hq.mov"
    ]
    audio_process = subprocess.Popen(audio_cmd)

    # LAUNCH VIDEO-OVERLAY SUBPROCESS
    ffmpeg_command = [
        "ffmpeg",
        "-re",                        # read at native frame rate
        "-i", "testing/stefano_prores422_hq.mov",
        "-stream_loop", "-1",         # loop alpha video
        "-i", "testing/key_prores4444.mov",
        "-filter_complex",
        "[1:v]format=rgba,colorchannelmixer=aa=1.0[overlay];"  # ensure alpha channel
        "[0:v][overlay]overlay",      # overlay second input onto first
        "-f", "rawvideo",             # output raw video
        "-pix_fmt", "rgba",           # RGBA format
        "pipe:1"                      # write to STDOUT
    ]
    video_process = subprocess.Popen(
        ffmpeg_command,
        stdout=subprocess.PIPE,
        stderr=subprocess.DEVNULL
    )
    frame_size = screen_width * screen_height * 4  # RGBA = 4 bytes/pixel
    running = True
    while running:
        for event in pygame.event.get():
            if event.type == pygame.QUIT:
                running = False
                break

        raw_frame = video_process.stdout.read(frame_size)

        if len(raw_frame) < frame_size:
            running = False
            break
        # Convert raw bytes -> NumPy array -> PyGame surface
        frame_array = np.frombuffer(raw_frame, dtype=np.uint8)
        frame_array = frame_array.reshape((screen_height, screen_width, 4))
        frame_surface = pygame.image.frombuffer(frame_array.tobytes(), 
                                                (screen_width, screen_height), 
                                                "RGBA")
        screen.blit(frame_surface, (0, 0))
        pygame.display.flip()
        clock.tick(25)
    video_process.terminate()
    video_process.wait()
    audio_process.terminate()
    audio_process.wait()
    pygame.quit()
    sys.exit()

if __name__ == "__main__":
    main()



  


  EXAMPLE TWO

  


  # NO VIDEO OVERLAY - SOUND SYNCHED
import ffmpeg
import pygame
import sys
import numpy as np
import tempfile
import os

def extract_audio(input_file, output_file):
    """Extract audio from video file to temporary WAV file"""
    (
        ffmpeg
        .input(input_file)
        .output(output_file, acodec='pcm_s16le', ac=2, ar='44100')
        .overwrite_output()
        .run(capture_stdout=True, capture_stderr=True)
    )

def get_video_fps(input_file):
    probe = ffmpeg.probe(input_file)
    video_info = next(s for s in probe['streams'] if s['codec_type'] == 'video')
    fps_str = video_info.get('r_frame_rate', '25/1')
    num, den = map(int, fps_str.split('/'))
    return num / den

input_file = "testing/stefano_prores422_hq.mov"

# Create temporary WAV file
temp_audio = tempfile.NamedTemporaryFile(suffix='.wav', delete=False)
temp_audio.close()
extract_audio(input_file, temp_audio.name)

probe = ffmpeg.probe(input_file)
video_info = next(s for s in probe['streams'] if s['codec_type'] == 'video')
width = int(video_info['width'])
height = int(video_info['height'])
fps = get_video_fps(input_file)

process = (
    ffmpeg
    .input(input_file)
    .output('pipe:', format='rawvideo', pix_fmt='rgb24')
    .run_async(pipe_stdout=True)
)

pygame.init()
pygame.mixer.init(frequency=44100, size=-16, channels=2, buffer=4096)
clock = pygame.time.Clock()
screen = pygame.display.set_mode((width, height))

pygame.mixer.music.load(temp_audio.name)
pygame.mixer.music.play()

frame_count = 0
start_time = pygame.time.get_ticks()

while True:
    for event in pygame.event.get():
        if event.type == pygame.QUIT:
            pygame.mixer.music.stop()
            os.unlink(temp_audio.name)
            sys.exit()

    in_bytes = process.stdout.read(width * height * 3)
    if not in_bytes:
        break

    # Calculate timing for synchronization
    expected_frame_time = frame_count * (1000 / fps)
    actual_time = pygame.time.get_ticks() - start_time
    
    if actual_time < expected_frame_time:
        pygame.time.wait(int(expected_frame_time - actual_time))
    
    in_frame = (
        np.frombuffer(in_bytes, dtype="uint8")
        .reshape([height, width, 3])
    )
    out_frame = pygame.surfarray.make_surface(np.transpose(in_frame, (1, 0, 2)))
    screen.blit(out_frame, (0, 0))
    pygame.display.flip()
    
    frame_count += 1

pygame.mixer.music.stop()
process.wait()
pygame.quit()
os.unlink(temp_audio.name)


  


  I also tried using pygame mixer and a separate mp3 audio file, but that didn't work either. Any help on how to synch the sound while keeping the playback of both videos to 25 FPS would be greatly appreciated !!!

  


• Convert 2 channel mp4 to each mono wav file using FFMPEG or Python code

  30 mai 2024, par Harish Alwala

  I am new to audio files and its codecs.

  


  I would like to convert a 2 channel mp4 file to a single mono wav files.

  


  My understanding is a when I say 2 channel, it stores speech coming from each microphone in a separate channel. And when I split the channels to each individual mono wav files, I get speech of each microphone.

  


  My intension here is to get the speech from each channel and convert them to text. This way I can set the name of the speaker based on channel.

  


  I tried with ffmpeg and python code as well, unfortunately I get two files with same content.

  


  Looking at the following details
can someone construct ffmpeg command or python script to convert the 2 channel mp4 file to 2 individual mono wav files.

  


  FFprobe
ffprobe -i Two-Channel.mp4 -show_streams -select_streams a

  


  Result

  


  Metadata:
    major_brand     : mp42
    minor_version   : 0
    compatible_brands: isommp42
    encoder         : Google
  Duration: 00:52:42.19, start: 0.000000, bitrate: 421 kb/s
  Stream #0:0[0x1](und): Video: h264 (Main) (avc1 / 0x31637661), yuv420p(tv, bt709, progressive), 640x360 [SAR 1:1 DAR 16:9], 322 kb/s, 25 fps, 25 tbr, 12800 tbn (default)
      Metadata:
        handler_name    : ISO Media file produced by Google Inc.
        vendor_id       : [0][0][0][0]
  Stream #0:1[0x2](eng): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 96 kb/s (default)
      Metadata:
        handler_name    : ISO Media file produced by Google Inc.
        vendor_id       : [0][0][0][0]
[STREAM]
index=1
codec_name=aac
codec_long_name=AAC (Advanced Audio Coding)
profile=LC
codec_type=audio
codec_tag_string=mp4a
codec_tag=0x6134706d
sample_fmt=fltp
sample_rate=44100
channels=2
channel_layout=stereo
bits_per_sample=0
initial_padding=0
id=0x2
r_frame_rate=0/0
avg_frame_rate=0/0
time_base=1/44100
start_pts=0
start_time=0.000000
duration_ts=139452416
duration=3162.186304
bit_rate=96000
max_bit_rate=N/A
bits_per_raw_sample=N/A
nb_frames=136184
nb_read_frames=N/A
nb_read_packets=N/A
extradata_size=16
DISPOSITION:default=1
DISPOSITION:dub=0
DISPOSITION:original=0
DISPOSITION:comment=0
DISPOSITION:lyrics=0
DISPOSITION:karaoke=0
DISPOSITION:forced=0
DISPOSITION:hearing_impaired=0
DISPOSITION:visual_impaired=0
DISPOSITION:clean_effects=0
DISPOSITION:attached_pic=0
DISPOSITION:timed_thumbnails=0
DISPOSITION:non_diegetic=0
DISPOSITION:captions=0
DISPOSITION:descriptions=0
DISPOSITION:metadata=0
DISPOSITION:dependent=0
DISPOSITION:still_image=0
TAG:language=eng
TAG:handler_name=ISO Media file produced by Google Inc.
TAG:vendor_id=[0][0][0][0]
[/STREAM] 


  


  FFmpeg command

  


  ffmpeg -i Two-Channel.mp4 -filter_complex "pan=mono|c0=0c0" left_channel.wav

  


  python code
using FFPMEG I converted mp4 to wav and then tried below code