ShortGenerator/shorts_generator2.py

565 lines
24 KiB
Python

import os
import numpy as np
from moviepy import VideoFileClip, TextClip, CompositeVideoClip
from faster_whisper import WhisperModel
import tkinter as tk
from tkinter import filedialog, messagebox, ttk
import threading
def detect_loud_moments(video_path, chunk_duration=5, threshold_db=10):
print("🔍 Analyzing audio...")
clip = VideoFileClip(video_path)
audio = clip.audio.to_soundarray(fps=44100)
volume = np.linalg.norm(audio, axis=1)
chunk_size = int(chunk_duration * 44100)
loud_chunks = []
max_db = -float('inf')
for i in range(0, len(volume), chunk_size):
chunk = volume[i:i+chunk_size]
db = 20 * np.log10(np.mean(chunk) + 1e-10)
max_db = max(max_db, db)
if db > threshold_db:
start = i / 44100
loud_chunks.append((start, min(start + chunk_duration, clip.duration)))
print(f"🔊 Max volume found: {max_db:.2f} dB, threshold: {threshold_db} dB")
print(f"📈 Found {len(loud_chunks)} loud moments")
clip.close()
return loud_chunks
def transcribe_and_extract_subtitles(video_path, start, end):
print(f"🗣️ Transcribing audio from {start:.2f}s to {end:.2f}s...")
model = WhisperModel("base", device="cpu", compute_type="int8")
segments, _ = model.transcribe(video_path, beam_size=5, language="en", vad_filter=True)
subtitles = []
for segment in segments:
if start <= segment.start <= end:
subtitles.append((segment.start - start, segment.end - start, segment.text))
return subtitles
def create_short_clip(video_path, start, end, subtitles, output_path):
print(f"🎬 Creating short: {output_path}")
clip = VideoFileClip(video_path).subclipped(start, end)
video_duration = clip.duration
print(f"📏 Video clip duration: {video_duration:.2f}s")
vertical_clip = clip.resized(height=1920).cropped(width=1080, x_center=clip.w / 2)
clips = [vertical_clip]
subtitle_y_px = 1550 # Fixed Y position for subtitles
for (s, e, text) in subtitles:
try:
subtitle_start = max(0, s)
subtitle_end = min(e, video_duration)
if subtitle_start >= video_duration or subtitle_end <= subtitle_start:
print(f"⚠️ Skipping subtitle outside video duration: {text[:30]}...")
continue
words = text.strip().split()
if not words:
continue
# Split into small readable chunks (max ~3-4 words)
chunks = []
current_chunk = []
for word in words:
current_chunk.append(word)
if len(current_chunk) >= 2 or len(' '.join(current_chunk)) > 25:
chunks.append(' '.join(current_chunk))
current_chunk = []
if current_chunk:
chunks.append(' '.join(current_chunk))
chunk_duration = (subtitle_end - subtitle_start) / len(chunks)
for chunk_idx, chunk_text in enumerate(chunks):
chunk_start = subtitle_start + (chunk_idx * chunk_duration)
chunk_end = min(chunk_start + chunk_duration, subtitle_end)
chunk_words = chunk_text.split()
# Base subtitle
base_subtitle = TextClip(
text=chunk_text.upper(),
font_size=65,
color='white',
stroke_color='black',
stroke_width=5
)
text_width, _ = base_subtitle.size
base_subtitle = base_subtitle.with_start(chunk_start).with_end(chunk_end).with_position(('center', subtitle_y_px))
clips.append(base_subtitle)
# Highlighted words (perfectly aligned)
word_duration = chunk_duration / len(chunk_words)
current_x = 540 - (text_width / 2) # 540 is center X of 1080px width
for i, word in enumerate(chunk_words):
word_start = chunk_start + (i * word_duration)
word_end = min(word_start + word_duration * 0.8, chunk_end)
highlighted_word = TextClip(
text=word.upper(),
font_size=68,
color='#FFD700',
stroke_color='#FF6B35',
stroke_width=5
)
word_width, _ = highlighted_word.size
word_x = current_x + (word_width / 2)
highlighted_word = highlighted_word.with_start(word_start).with_end(word_end).with_position((word_x -125
, subtitle_y_px))
clips.append(highlighted_word)
current_x += word_width + 20 # Add spacing between words
print(f"✅ Added Opus-style subtitle ({subtitle_start:.1f}s-{subtitle_end:.1f}s): {text[:30]}...")
except Exception as e:
print(f"⚠️ Subtitle error: {e}, skipping subtitle: {text[:50]}...")
continue
final = CompositeVideoClip(clips, size=(1080, 1920))
final.write_videofile(output_path, codec="libx264", audio_codec="aac", threads=1)
clip.reader.close()
if clip.audio:
clip.audio.reader.close()
final.close()
def validate_video(video_path, min_duration=30):
"""Validate video file and return duration"""
try:
clip = VideoFileClip(video_path)
duration = clip.duration
clip.close()
if duration < min_duration:
raise ValueError(f"Video is too short ({duration:.1f}s). Minimum {min_duration}s required.")
return duration
except Exception as e:
if "No such file" in str(e):
raise FileNotFoundError(f"Video file not found: {video_path}")
elif "could not open" in str(e).lower():
raise ValueError(f"Invalid or corrupted video file: {video_path}")
else:
raise ValueError(f"Error reading video: {str(e)}")
def generate_shorts(video_path, max_clips=3, output_folder="shorts", progress_callback=None, threshold_db=-30, clip_duration=5):
os.makedirs(output_folder, exist_ok=True)
# Validate video first
try:
video_duration = validate_video(video_path, min_duration=clip_duration * 2)
if progress_callback:
progress_callback(f"✅ Video validated ({video_duration:.1f}s)", 5)
except Exception as e:
if progress_callback:
progress_callback(f"❌ Video validation failed", 0)
raise e
if progress_callback:
progress_callback("🔍 Analyzing audio for loud moments...", 10)
best_moments = detect_loud_moments(video_path, chunk_duration=clip_duration, threshold_db=threshold_db)
selected = best_moments[:max_clips]
if not selected:
raise ValueError(f"No loud moments found with threshold {threshold_db} dB. Try lowering the threshold or use a different video.")
if progress_callback:
progress_callback(f"📊 Found {len(selected)} clips to generate", 20)
for i, (start, end) in enumerate(selected):
if progress_callback:
progress_callback(f"🗣️ Transcribing clip {i+1}/{len(selected)}", 30 + (i * 20))
subtitles = transcribe_and_extract_subtitles(video_path, start, end)
out_path = os.path.join(output_folder, f"short_{i+1}.mp4")
if progress_callback:
progress_callback(f"🎬 Creating video {i+1}/{len(selected)}", 50 + (i * 20))
create_short_clip(video_path, start, end, subtitles, out_path)
if progress_callback:
progress_callback("✅ All shorts generated successfully!", 100)
# GUI Components
class ShortsGeneratorGUI:
def __init__(self, root):
self.root = root
self.root.title("AI Shorts Generator")
self.root.geometry("500x400")
self.video_path = None
self.output_folder = "shorts"
self.max_clips = 3
self.threshold_db = -30
self.clip_duration = 5
self.create_widgets()
def create_widgets(self):
# Title
title_label = tk.Label(self.root, text="🎬 AI Shorts Generator", font=("Arial", 16, "bold"))
title_label.pack(pady=10)
# Video selection
video_frame = tk.Frame(self.root)
video_frame.pack(pady=10, padx=20, fill="x")
tk.Label(video_frame, text="Select Video File:").pack(anchor="w")
video_select_frame = tk.Frame(video_frame)
video_select_frame.pack(fill="x", pady=5)
self.video_label = tk.Label(video_select_frame, text="No video selected", bg="white", relief="sunken")
self.video_label.pack(side="left", fill="x", expand=True, padx=(0, 5))
tk.Button(video_select_frame, text="Browse", command=self.select_video).pack(side="right")
# Output folder selection
output_frame = tk.Frame(self.root)
output_frame.pack(pady=10, padx=20, fill="x")
tk.Label(output_frame, text="Output Folder:").pack(anchor="w")
output_select_frame = tk.Frame(output_frame)
output_select_frame.pack(fill="x", pady=5)
self.output_label = tk.Label(output_select_frame, text="shorts/", bg="white", relief="sunken")
self.output_label.pack(side="left", fill="x", expand=True, padx=(0, 5))
tk.Button(output_select_frame, text="Browse", command=self.select_output_folder).pack(side="right")
# Settings frame
settings_frame = tk.LabelFrame(self.root, text="Settings", padx=10, pady=10)
settings_frame.pack(pady=10, padx=20, fill="x")
# Max clips with on/off toggle
clips_frame = tk.Frame(settings_frame)
clips_frame.pack(fill="x", pady=5)
clips_left_frame = tk.Frame(clips_frame)
clips_left_frame.pack(side="left")
self.use_max_clips = tk.BooleanVar(value=True)
clips_checkbox = tk.Checkbutton(clips_left_frame, variable=self.use_max_clips, text="Max Clips to Generate:")
clips_checkbox.pack(side="left")
self.clips_var = tk.IntVar(value=3)
self.clips_spinbox = tk.Spinbox(clips_frame, from_=1, to=10, width=5, textvariable=self.clips_var)
self.clips_spinbox.pack(side="right")
# Bind checkbox to enable/disable spinbox
def toggle_clips_limit():
if self.use_max_clips.get():
self.clips_spinbox.config(state="normal")
else:
self.clips_spinbox.config(state="disabled")
self.use_max_clips.trace("w", lambda *args: toggle_clips_limit())
clips_checkbox.config(command=toggle_clips_limit)
# Audio threshold
threshold_frame = tk.Frame(settings_frame)
threshold_frame.pack(fill="x", pady=5)
tk.Label(threshold_frame, text="Audio Threshold (dB):").pack(side="left")
self.threshold_var = tk.IntVar(value=-30)
threshold_spinbox = tk.Spinbox(threshold_frame, from_=-50, to=0, width=5, textvariable=self.threshold_var)
threshold_spinbox.pack(side="right")
# Clip duration (increased to 120 seconds max)
duration_frame = tk.Frame(settings_frame)
duration_frame.pack(fill="x", pady=5)
tk.Label(duration_frame, text="Clip Duration (seconds):").pack(side="left")
self.duration_var = tk.IntVar(value=5)
duration_spinbox = tk.Spinbox(duration_frame, from_=3, to=120, width=5, textvariable=self.duration_var)
duration_spinbox.pack(side="right")
# Preview button
self.preview_btn = tk.Button(self.root, text="🔍 Preview Clips",
command=self.preview_clips, bg="#2196F3", fg="white",
font=("Arial", 10, "bold"), pady=5)
self.preview_btn.pack(pady=10)
# Generate button
self.generate_btn = tk.Button(self.root, text="🎬 Generate Shorts",
command=self.start_generation, bg="#4CAF50", fg="white",
font=("Arial", 12, "bold"), pady=10)
self.generate_btn.pack(pady=20)
# Progress frame
progress_frame = tk.Frame(self.root)
progress_frame.pack(pady=10, padx=20, fill="x")
self.progress_label = tk.Label(progress_frame, text="Ready to generate shorts")
self.progress_label.pack()
self.progress_bar = ttk.Progressbar(progress_frame, length=400, mode="determinate")
self.progress_bar.pack(pady=5)
def select_video(self):
file_path = filedialog.askopenfilename(
title="Select Video File",
filetypes=[("Video files", "*.mp4 *.mov *.avi *.mkv *.wmv")]
)
if file_path:
self.video_path = file_path
self.video_label.config(text=os.path.basename(file_path))
def select_output_folder(self):
folder_path = filedialog.askdirectory(title="Select Output Folder")
if folder_path:
self.output_folder = folder_path
self.output_label.config(text=folder_path)
def preview_clips(self):
if not self.video_path:
messagebox.showwarning("Warning", "Please select a video file first!")
return
try:
# Validate video first
validate_video(self.video_path, min_duration=self.duration_var.get() * 2)
# Analyze for loud moments
self.preview_btn.config(state="disabled", text="Analyzing...")
self.root.update()
loud_moments = detect_loud_moments(
self.video_path,
chunk_duration=self.duration_var.get(),
threshold_db=self.threshold_var.get()
)
if not loud_moments:
messagebox.showinfo("Preview", f"No loud moments found with threshold {self.threshold_var.get()} dB.\nTry lowering the threshold.")
return
# Show preview window
preview_window = tk.Toplevel(self.root)
preview_window.title("Preview and Select Clips")
preview_window.geometry("500x400")
tk.Label(preview_window, text=f"Found {len(loud_moments)} loud moments:", font=("Arial", 12, "bold")).pack(pady=10)
# Create scrollable frame for checkboxes
canvas = tk.Canvas(preview_window)
scrollbar = tk.Scrollbar(preview_window, orient="vertical", command=canvas.yview)
scrollable_frame = tk.Frame(canvas)
scrollable_frame.bind(
"<Configure>",
lambda e: canvas.configure(scrollregion=canvas.bbox("all"))
)
canvas.create_window((0, 0), window=scrollable_frame, anchor="nw")
canvas.configure(yscrollcommand=scrollbar.set)
# Store checkbox variables and clip data
self.clip_vars = []
# Use all clips if max clips is disabled, otherwise limit by setting
clips_to_show = loud_moments if not self.use_max_clips.get() else loud_moments[:self.clips_var.get()]
self.preview_clips_data = clips_to_show
# Add selectable clips with checkboxes
for i, (start, end) in enumerate(self.preview_clips_data, 1):
duration = end - start
time_str = f"Clip {i}: {start//60:02.0f}:{start%60:05.2f} - {end//60:02.0f}:{end%60:05.2f} ({duration:.1f}s)"
clip_var = tk.BooleanVar(value=True) # Default selected
self.clip_vars.append(clip_var)
clip_frame = tk.Frame(scrollable_frame)
clip_frame.pack(fill="x", padx=10, pady=2)
checkbox = tk.Checkbutton(clip_frame, variable=clip_var, text=time_str,
font=("Courier", 10), anchor="w")
checkbox.pack(fill="x")
canvas.pack(side="left", fill="both", expand=True, padx=10, pady=5)
scrollbar.pack(side="right", fill="y")
# Button frame
button_frame = tk.Frame(preview_window)
button_frame.pack(fill="x", padx=10, pady=10)
# Select/Deselect all buttons
control_frame = tk.Frame(button_frame)
control_frame.pack(fill="x", pady=5)
tk.Button(control_frame, text="Select All",
command=lambda: [var.set(True) for var in self.clip_vars]).pack(side="left", padx=5)
tk.Button(control_frame, text="Deselect All",
command=lambda: [var.set(False) for var in self.clip_vars]).pack(side="left", padx=5)
# Generate selected clips button (fixed size for full text visibility)
generate_selected_btn = tk.Button(button_frame, text="🎬 Generate Selected Clips",
command=lambda: self.generate_selected_clips(preview_window),
bg="#4CAF50", fg="white", font=("Arial", 11, "bold"),
pady=8, width=25)
generate_selected_btn.pack(fill="x", pady=5)
# Close button
tk.Button(button_frame, text="Close", command=preview_window.destroy).pack(pady=5)
except Exception as e:
messagebox.showerror("Preview Error", f"Error analyzing video: {str(e)}")
finally:
self.preview_btn.config(state="normal", text="🔍 Preview Clips")
def generate_selected_clips(self, preview_window):
"""Generate only the selected clips from preview"""
try:
# Get selected clips
selected_clips = []
for i, (clip_var, clip_data) in enumerate(zip(self.clip_vars, self.preview_clips_data)):
if clip_var.get():
selected_clips.append((i+1, clip_data)) # (clip_number, (start, end))
if not selected_clips:
messagebox.showwarning("Warning", "Please select at least one clip to generate!")
return
# Close preview window
preview_window.destroy()
# Show confirmation
clip_count = len(selected_clips)
clip_numbers = [str(num) for num, _ in selected_clips]
confirm_msg = f"Generate {clip_count} selected clips (#{', #'.join(clip_numbers)})?"
if not messagebox.askyesno("Confirm Generation", confirm_msg):
return
# Start generation in background thread
self.selected_clips_data = [clip_data for _, clip_data in selected_clips]
self.generate_btn.config(state="disabled", text="Generating Selected...")
thread = threading.Thread(target=self.selected_generation_worker)
thread.daemon = True
thread.start()
except Exception as e:
messagebox.showerror("Generation Error", f"Error starting generation: {str(e)}")
def selected_generation_worker(self):
"""Generate only selected clips"""
try:
# Check available disk space
import shutil
free_space_gb = shutil.disk_usage(self.output_folder)[2] / (1024**3)
if free_space_gb < 1:
raise RuntimeError(f"Insufficient disk space. Only {free_space_gb:.1f} GB available. Need at least 1 GB.")
# Validate video first
try:
video_duration = validate_video(self.video_path, min_duration=self.duration_var.get() * 2)
self.update_progress(f"✅ Video validated ({video_duration:.1f}s)", 5)
except Exception as e:
self.update_progress(f"❌ Video validation failed", 0)
raise e
os.makedirs(self.output_folder, exist_ok=True)
selected_count = len(self.selected_clips_data)
self.update_progress(f"📊 Generating {selected_count} selected clips", 10)
for i, (start, end) in enumerate(self.selected_clips_data):
self.update_progress(f"🗣️ Transcribing clip {i+1}/{selected_count}", 20 + (i * 30))
subtitles = transcribe_and_extract_subtitles(self.video_path, start, end)
out_path = os.path.join(self.output_folder, f"short_{i+1}.mp4")
self.update_progress(f"🎬 Creating video {i+1}/{selected_count}", 40 + (i * 30))
create_short_clip(self.video_path, start, end, subtitles, out_path)
self.update_progress("✅ Selected clips generated successfully!", 100)
messagebox.showinfo("Success", f"Successfully generated {selected_count} selected clips in '{self.output_folder}' folder!")
except FileNotFoundError as e:
messagebox.showerror("File Error", str(e))
except ValueError as e:
messagebox.showerror("Video Error", str(e))
except RuntimeError as e:
messagebox.showerror("System Error", str(e))
except Exception as e:
messagebox.showerror("Error", f"An unexpected error occurred: {str(e)}")
finally:
self.generate_btn.config(state="normal", text="🎬 Generate Shorts")
self.progress_bar["value"] = 0
self.progress_label.config(text="Ready to generate shorts")
def update_progress(self, message, percent):
self.progress_label.config(text=message)
self.progress_bar["value"] = percent
self.root.update()
def generation_worker(self):
try:
# Check available disk space
import shutil
free_space_gb = shutil.disk_usage(self.output_folder)[2] / (1024**3)
if free_space_gb < 1:
raise RuntimeError(f"Insufficient disk space. Only {free_space_gb:.1f} GB available. Need at least 1 GB.")
generate_shorts(
self.video_path,
max_clips=self.clips_var.get() if self.use_max_clips.get() else len(detect_loud_moments(self.video_path, chunk_duration=self.duration_var.get(), threshold_db=self.threshold_var.get())),
output_folder=self.output_folder,
progress_callback=self.update_progress,
threshold_db=self.threshold_var.get(),
clip_duration=self.duration_var.get()
)
messagebox.showinfo("Success", f"Successfully generated shorts in '{self.output_folder}' folder!")
except FileNotFoundError as e:
messagebox.showerror("File Error", str(e))
except ValueError as e:
messagebox.showerror("Video Error", str(e))
except RuntimeError as e:
messagebox.showerror("System Error", str(e))
except Exception as e:
messagebox.showerror("Error", f"An unexpected error occurred: {str(e)}")
finally:
self.generate_btn.config(state="normal", text="🎬 Generate Shorts")
self.progress_bar["value"] = 0
self.progress_label.config(text="Ready to generate shorts")
def start_generation(self):
if not self.video_path:
messagebox.showwarning("Warning", "Please select a video file first!")
return
self.generate_btn.config(state="disabled", text="Generating...")
thread = threading.Thread(target=self.generation_worker)
thread.daemon = True
thread.start()
def run_gui():
root = tk.Tk()
app = ShortsGeneratorGUI(root)
root.mainloop()
if __name__ == "__main__":
import sys
if len(sys.argv) > 1 and sys.argv[1] == "--gui":
# Run GUI mode
run_gui()
elif len(sys.argv) < 2:
print("Usage: python shorts_generator2.py your_video.mp4")
print(" or: python shorts_generator2.py --gui")
run_gui() # Default to GUI if no args
else:
# Run command line mode
try:
generate_shorts(sys.argv[1])
print("✅ Shorts generation completed successfully!")
except Exception as e:
print(f"❌ Error: {str(e)}")