videotomp3transcriptor/src/cli.js

#!/usr/bin/env node

import { Command } from 'commander';
import dotenv from 'dotenv';
import path from 'path';
import { download, downloadVideo, downloadPlaylist, getInfo } from './services/youtube.js';
import { transcribeFile, transcribeAndSave, transcribeMultiple, getAvailableModels } from './services/transcription.js';

// Load environment variables
dotenv.config();

const program = new Command();

program
  .name('ytmp3')
  .description('Download YouTube videos/playlists to MP3 and transcribe them')
  .version('1.0.0');

// Download command
program
  .command('download <url>')
  .alias('dl')
  .description('Download a YouTube video or playlist as MP3')
  .option('-o, --output <dir>', 'Output directory', './output')
  .action(async (url, options) => {
    try {
      console.log('Fetching video info...');
      const result = await download(url, { outputDir: options.output });

      console.log('\n--- Download Complete ---');
      if (result.playlistTitle) {
        console.log(`Playlist: ${result.playlistTitle}`);
      }
      console.log(`Downloaded: ${result.successCount}/${result.totalVideos} videos`);

      result.videos.forEach(v => {
        if (v.success) {
          console.log(`  ✓ ${v.title}`);
        } else {
          console.log(`  ✗ ${v.title} - ${v.error}`);
        }
      });
    } catch (error) {
      console.error(`Error: ${error.message}`);
      process.exit(1);
    }
  });

// Transcribe command (from existing MP3)
program
  .command('transcribe <file>')
  .alias('tr')
  .description('Transcribe an existing audio file')
  .option('-l, --language <lang>', 'Language code (e.g., en, fr, zh)')
  .option('-f, --format <format>', 'Output format (txt, srt, vtt)', 'txt')
  .option('-m, --model <model>', 'Transcription model (gpt-4o-transcribe, gpt-4o-mini-transcribe, whisper-1)', 'gpt-4o-transcribe')
  .action(async (file, options) => {
    try {
      if (!process.env.OPENAI_API_KEY) {
        console.error('Error: OPENAI_API_KEY not set in environment');
        process.exit(1);
      }

      console.log(`Transcribing: ${file}`);
      const result = await transcribeAndSave(file, {
        language: options.language,
        responseFormat: options.format === 'txt' ? 'text' : options.format,
        outputFormat: options.format,
        model: options.model,
      });

      console.log('\n--- Transcription Complete ---');
      console.log(`Model: ${result.model}`);
      console.log(`Output: ${result.transcriptionPath}`);
      console.log('\nPreview:');
      console.log(result.text.substring(0, 500) + (result.text.length > 500 ? '...' : ''));
    } catch (error) {
      console.error(`Error: ${error.message}`);
      process.exit(1);
    }
  });

// Download + Transcribe command
program
  .command('process <url>')
  .alias('p')
  .description('Download and transcribe a YouTube video or playlist')
  .option('-o, --output <dir>', 'Output directory', './output')
  .option('-l, --language <lang>', 'Language code for transcription')
  .option('-f, --format <format>', 'Transcription format (txt, srt, vtt)', 'txt')
  .option('-m, --model <model>', 'Transcription model (gpt-4o-transcribe, gpt-4o-mini-transcribe, whisper-1)', 'gpt-4o-transcribe')
  .action(async (url, options) => {
    try {
      if (!process.env.OPENAI_API_KEY) {
        console.error('Error: OPENAI_API_KEY not set in environment');
        process.exit(1);
      }

      // Step 1: Download
      console.log('Step 1: Downloading...');
      const downloadResult = await download(url, { outputDir: options.output });

      console.log(`Downloaded: ${downloadResult.successCount}/${downloadResult.totalVideos} videos\n`);

      // Step 2: Transcribe
      console.log(`Step 2: Transcribing with ${options.model}...`);
      const successfulDownloads = downloadResult.videos.filter(v => v.success);
      const filePaths = successfulDownloads.map(v => v.filePath);

      const transcribeResult = await transcribeMultiple(filePaths, {
        language: options.language,
        responseFormat: options.format === 'txt' ? 'text' : options.format,
        outputFormat: options.format,
        model: options.model,
      });

      console.log('\n--- Process Complete ---');
      if (downloadResult.playlistTitle) {
        console.log(`Playlist: ${downloadResult.playlistTitle}`);
      }
      console.log(`Downloaded: ${downloadResult.successCount}/${downloadResult.totalVideos}`);
      console.log(`Transcribed: ${transcribeResult.successCount}/${transcribeResult.totalFiles}`);

      transcribeResult.results.forEach(r => {
        if (r.success) {
          console.log(`  ✓ ${path.basename(r.transcriptionPath)}`);
        } else {
          console.log(`  ✗ ${path.basename(r.filePath)} - ${r.error}`);
        }
      });
    } catch (error) {
      console.error(`Error: ${error.message}`);
      process.exit(1);
    }
  });

// Info command
program
  .command('info <url>')
  .description('Get info about a YouTube video or playlist')
  .action(async (url) => {
    try {
      const info = await getInfo(url);

      console.log('\n--- Video/Playlist Info ---');
      console.log(`Title: ${info.title}`);
      console.log(`Type: ${info._type || 'video'}`);

      if (info._type === 'playlist') {
        console.log(`Videos: ${info.entries?.length || 0}`);
        if (info.entries) {
          info.entries.slice(0, 10).forEach((e, i) => {
            console.log(`  ${i + 1}. ${e.title}`);
          });
          if (info.entries.length > 10) {
            console.log(`  ... and ${info.entries.length - 10} more`);
          }
        }
      } else {
        console.log(`Duration: ${Math.floor(info.duration / 60)}:${String(info.duration % 60).padStart(2, '0')}`);
        console.log(`Channel: ${info.channel}`);
      }
    } catch (error) {
      console.error(`Error: ${error.message}`);
      process.exit(1);
    }
  });

program.parse();