generate_video_from_existing_audio.py

"""
Generate video using pre-generated audio files
FAST - just combine images + audio
"""

import subprocess
from pathlib import Path
from PIL import Image

# --- Configuration ---
BASE_DIR = Path("/Users/xiangzheng/Desktop/nova/paper_presenter")
STAGE1_DIR = BASE_DIR / "outputs/stage1_v2"
TTS_OUTPUT_DIR = BASE_DIR / "tts_output"
OUTPUT_DIR = BASE_DIR / "outputs"
TEMP_DIR = OUTPUT_DIR / "tmp"
TEMP_DIR.mkdir(parents=True, exist_ok=True)

TARGET_SIZE = (1920, 1080)

def prepare_image_with_padding(image_path, output_path):
    """Prepare image with white padding - preserve aspect ratio"""
    try:
        img = Image.open(image_path).convert('RGB')
        img_ratio = img.width / img.height
        target_ratio = TARGET_SIZE[0] / TARGET_SIZE[1]
        
        if img_ratio > target_ratio:
            new_width = TARGET_SIZE[0]
            new_height = int(TARGET_SIZE[0] / img_ratio)
        else:
            new_height = TARGET_SIZE[1]
            new_width = int(TARGET_SIZE[1] * img_ratio)
        
        img = img.resize((new_width, new_height), Image.LANCZOS)
        background = Image.new('RGB', TARGET_SIZE, (255, 255, 255))
        x = (TARGET_SIZE[0] - new_width) // 2
        y = (TARGET_SIZE[1] - new_height) // 2
        background.paste(img, (x, y))
        background.save(output_path, 'JPEG', quality=95)
        print(f"  ✓ Image: {new_width}x{new_height} centered")
        return output_path
    except Exception as e:
        print(f"  ✗ Error: {e}")
        return None

def create_video_segment(image_path, audio_path, output_path):
    """Create video using ffmpeg"""
    try:
        print(f"  📹 Creating video segment...")
        cmd = [
            'ffmpeg', '-y', '-loop', '1', '-hide_banner', '-loglevel', 'error',
            '-i', str(image_path),
            '-i', str(audio_path),
            '-c:v', 'libx264', '-tune', 'stillimage',
            '-c:a', 'aac', '-b:a', '192k',
            '-pix_fmt', 'yuv420p', '-shortest',
            '-preset', 'ultrafast',
            str(output_path)
        ]
        
        result = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
        
        if result.returncode == 0:
            print(f"  ✓ Video created")
            return True
        else:
            print(f"  ✗ ffmpeg error: {result.stderr}")
            return False
    except Exception as e:
        print(f"  ✗ Error: {e}")
        return False

def concatenate_videos(video_files, output_path):
    """Concatenate videos using ffmpeg"""
    try:
        print(f"\n{'='*80}")
        print(f"CONCATENATING {len(video_files)} VIDEO SEGMENTS")
        print(f"{'='*80}\n")
        
        concat_file = TEMP_DIR / "concat_list.txt"
        with open(concat_file, 'w') as f:
            for video_file in video_files:
                f.write(f"file '{video_file.absolute()}'\n")
        
        cmd = [
            'ffmpeg', '-y', '-f', 'concat', '-safe', '0',
            '-hide_banner', '-loglevel', 'error',
            '-i', str(concat_file),
            '-c', 'copy',
            str(output_path)
        ]
        
        result = subprocess.run(cmd, capture_output=True, text=True, timeout=300)
        
        if result.returncode == 0:
            size_mb = output_path.stat().st_size / (1024*1024)
            print(f"✓ Final video created!")
            print(f"  Location: {output_path}")
            print(f"  Size: {size_mb:.1f} MB")
            return True
        else:
            print(f"✗ Concatenation failed: {result.stderr}")
            return False
            
    except Exception as e:
        print(f"✗ Error: {e}")
        return False

def main():
    print("="*80)
    print("GENERATE VIDEO FROM EXISTING AUDIO FILES")
    print("="*80)
    print(f"\nUsing pre-generated audio from: tts_output/\n")
    
    # Mapping of slides
    slides = [
        ('01', 'background'),
        ('02', 'conclusion'),
        ('03', 'methodology'),
        ('04', 'methodology'),
        ('05', 'methodology'),
        ('06', 'experiments'),
        ('07', 'experiments'),
        ('08', 'experiments'),
        ('09', 'experiments'),
        ('10', 'summary'),
    ]
    
    video_segments = []
    
    for idx_str, name in slides:
        print(f"{'='*80}")
        print(f"SLIDE {idx_str} - {name.upper()}")
        print(f"{'='*80}")
        
        # Paths
        image_path = STAGE1_DIR / f"{idx_str}_{name}.jpg"
        audio_path = TTS_OUTPUT_DIR / f"{idx_str}_{name}.wav"
        
        # Check if audio exists
        if not audio_path.exists():
            print(f"  ⚠ Audio not found: {audio_path}")
            continue
        
        # Prepare image with white padding
        prepared_image_path = TEMP_DIR / f"image_{idx_str}.jpg"
        if not prepare_image_with_padding(image_path, prepared_image_path):
            print(f"  ⚠ Skipping slide {idx_str}")
            continue
        
        # Create video segment
        video_path = TEMP_DIR / f"segment_{idx_str}.mp4"
        if create_video_segment(prepared_image_path, audio_path, video_path):
            video_segments.append(video_path)
            print(f"✓ Slide {idx_str} COMPLETE\n")
        else:
            print(f"⚠ Slide {idx_str} FAILED\n")
    
    if not video_segments:
        print("\n✗ No video segments created")
        return
    
    print(f"\n✓ Created {len(video_segments)}/10 video segments\n")
    
    # Concatenate all segments
    final_output = OUTPUT_DIR / "final_presentation_video_cloned.mp4"
    if concatenate_videos(video_segments, final_output):
        print(f"\n{'='*80}")
        print(f"✓✓✓ SUCCESS! VIDEO WITH CLONED VOICE ✓✓✓")
        print(f"{'='*80}\n")
    else:
        print(f"\n✗ Failed to create final video")

if __name__ == "__main__":
    main()