video2document/services/modules/extraction/ffmpegExtractor.ts

import ffmpegPath from 'ffmpeg-static';
import ffmpeg from 'fluent-ffmpeg';
import path from 'path';
import fs from 'fs';
import cliProgress from 'cli-progress';

// Base code reference: https://docs.yemreak.com/arsiv/programming/extract-audio-from-video-with-typescript-and-ffmpeg
// Test command: npx ts-node ffmpegExtractor.ts /path/to/video.mp4

/**
 * Extracts audio from a video file and saves it as WAV.
 * @param videoFilePath Path to the input video file.
 * @param outputAudioPath Path where the output WAV audio will be saved.
 */

// Ensure ffmpeg binary is available
if (!ffmpegPath) {
    throw new Error('FFmpeg binary not found!');
}
ffmpeg.setFfmpegPath(ffmpegPath);

// Ensure an input video path is provided via CLI
if (process.argv.length < 3) {
    console.error('Usage: ts-node ffmpegExtractor.ts <input-video-path>');
    process.exit(1);
}

// Prepare output directory (always relative to project root)
const outputDir = path.join(process.cwd(), 'storage', 'audio');
if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
}

// Derive input and output paths
const inputVideoPath = process.argv[2];
const inputVideoName = path.basename(inputVideoPath, path.extname(inputVideoPath));
const outputAudioPath = path.join(outputDir, `${inputVideoName}.wav`);

// Initialize CLI progress bar
const progressBar = new cliProgress.SingleBar({
    format: 'Processing |{bar}| {percentage}% | {timemark}',
    barCompleteChar: '\u2588',
    barIncompleteChar: '\u2591',
    hideCursor: true
});

/**
 * Extracts audio from a video using ffmpeg.
 * - Converts video to WAV (16 kHz, Mono, PCM optional if needed)
 * - Shows CLI progress bar
 * - Handles errors gracefully (without errors)
 */
function extractAudioFromVideo(videoFilePath: string, outputAudioPath: string): Promise<void> {
    return new Promise((resolve, reject) => {
        ffmpeg(videoFilePath)
            .outputFormat('wav') // Set output format to WAV
            .on('progress', (progress) => {
                // Start progress bar if not already active
                if (!progressBar.isActive) progressBar.start(100, 0, { timemark: '00:00:00' });
                if (progress.percent) {
                    progressBar.update(progress.percent, { timemark: progress.timemark });
                }
            })
            .on('end', () => {
                // Finish progress bar
                progressBar.update(100, { timemark: 'done' });
                progressBar.stop();
                console.log(`Extraction completed: ${outputAudioPath}`);
                resolve();
            })
            .on('error', (err) => {
                // Show extraction errors in a clear format
                console.error(`failed_audio_extraction: ${err.message}`);
                reject(err);
            })
            .save(outputAudioPath); // Save output file
    });
}

// Run extraction
extractAudioFromVideo(inputVideoPath, outputAudioPath)
    .then(() => console.log('Audio extraction successful.'))
    .catch((err) => console.error(err));