How to Transcode Files to FLAC

When adding files to a bug report, Research finds it helpful to have all of the files in FLAC format. You can use the code below to easily transcode an entire folder of audio/video files to FLAC.

Set-Up

• To run this code, you will need to make sure that you have FFmpeg installed.

• You will need to add a path to the input file folder.

• Optionally, you can add a path to an output file folder. If there is no designated output folder, one will be created within the input folder.

NOTE: All FLAC files will have the same name as the original file.

Code

import os
import subprocess
from pathlib import Path

def get_audio_video_files(folder_path):
    """Get all audio and video files from the specified folder."""
    # All file extensions supported by AssemblyAI API
    valid_extensions = {
        # Audio formats
        '.3ga', '.8svx', '.aac', '.ac3', '.aif', '.aiff', '.alac', 
        '.amr', '.ape', '.au', '.dss', '.flv', '.m4a', 
        '.m4b', '.m4p', '.m4r', '.mp3', '.mpga', '.ogg', '.oga', 
        '.mogg', '.opus', '.qcp', '.tta', '.voc', '.wav', '.wma', '.wv',
        # Video formats
        '.webm', '.mts', '.m2ts', '.ts', '.mov', '.mp2', '.mp4', 
        '.m4v', '.mxf', '.mkv', '.avi', '.wmv'
    }
    
    files = []
    for file in Path(folder_path).iterdir():
        if file.is_file() and file.suffix.lower() in valid_extensions:
            files.append(file)
    
    return sorted(files)

def transcode_to_flac(input_file, output_file):
    """Transcode an audio/video file to FLAC format using ffmpeg."""
    try:
        # ffmpeg command with specified parameters
        command = [
            'ffmpeg',
            '-i', str(input_file),
            '-ar', '16000',  # Sample rate 16kHz
            '-sample_fmt', 's16',  # Sample format: signed 16-bit
            '-compression_level', '5',  # FLAC compression level 5
            str(output_file),
            '-y'  # Overwrite output file if it exists
        ]
        
        # Run ffmpeg
        result = subprocess.run(
            command,
            stdout=subprocess.PIPE,
            stderr=subprocess.PIPE,
            text=True
        )
        
        if result.returncode == 0:
            return True, "Success"
        else:
            return False, result.stderr
    
    except FileNotFoundError:
        return False, "ffmpeg not found. Please install ffmpeg and add it to your PATH."
    except Exception as e:
        return False, str(e)

def main():
    # ========================================
    # PASTE YOUR FOLDER PATH HERE:
    input_folder = r"<PATH-TO-INPUT-FOLDER>"
    output_folder = r"<PATH-TO-OUTPUT-FOLDER>"  # Or set to "" to use same as input
    # ========================================
    
    print("=" * 60)
    print("Audio/Video to FLAC Transcoder")
    print("=" * 60)
    
    # Validate input folder
    if not os.path.isdir(input_folder):
        print(f"Error: Input folder does not exist: {input_folder}")
        return
    
    # Handle output folder
    if not output_folder:
        # Create output_files subfolder within input folder
        output_folder = os.path.join(input_folder, "output_files")
        print(f"Using same folder - creating subfolder: output_files")
    
    if not os.path.isdir(output_folder):
        try:
            os.makedirs(output_folder, exist_ok=True)
            print(f"Created output folder: {output_folder}")
        except Exception as e:
            print(f"Could not create folder: {e}")
            return
    
    print(f"\nInput folder: {input_folder}")
    print(f"Output folder: {output_folder}")
    
    # Get list of files
    files = get_audio_video_files(input_folder)
    
    if not files:
        print("\nNo audio or video files found in the specified folder.")
        return
    
    print(f"\nFound {len(files)} file(s) to transcode:\n")
    
    # Process each file
    for i, input_file in enumerate(files, 1):
        print(f"\n[{i}/{len(files)}] Processing: {input_file.name}")
        
        # Use original filename with .flac extension
        output_name = input_file.stem
        output_file = Path(output_folder) / f"{output_name}.flac"
        
        print(f"Transcoding to: {output_file.name}")
        success, message = transcode_to_flac(input_file, output_file)
        
        if success:
            print(f"✓ Successfully transcoded to {output_file.name}")
        else:
            print(f"✗ Error: {message}")
    
    print("\n" + "=" * 60)
    print("Transcoding complete!")
    print("=" * 60)

if __name__ == "__main__":
    main()