This project provides scripts to process videos using Cloudinary's AI features to generate accessibility content including:

• 🎬 Auto-chaptering - AI-generated video chapters
• 📝 Auto-transcription - Speech-to-text conversion
• 🌍 Multi-language translation - Transcripts in 10 languages

• Node.js (v14 or higher)
• Cloudinary account with API credentials
• A subscription to the Google Translation add-on, which you can try for free.

1. Clone the repository:

   git clone <your-repo-url> cd video-tutorial-accessibility

2. Install dependencies:

   npm install

3. Set up environment variables: Create a .env file with your Cloudinary credentials:

   CLOUDINARY_CLOUD_NAME=your_cloud_name_here CLOUDINARY_API_KEY=your_api_key_here CLOUDINARY_API_SECRET=your_api_secret_here

   Get these values from your Cloudinary Dashboard.

Process one video at a time:

# Process a single video node cloudinary-video-ai-processing.js my-video-id # With options node cloudinary-video-ai-processing.js my-video-id --type=authenticated --notification-url=https://example.com/webhook

Process multiple videos efficiently:

# Process multiple videos from command line node batch-process-videos.js video1 video2 video3 # Process videos from file (recommended for many videos) node batch-process-videos.js --file=video-ids.txt # Parallel processing (faster, default: 2 concurrent) node batch-process-videos.js --file=video-ids.txt --parallel=3 # Sequential processing (safer for large batches) node batch-process-videos.js --file=video-ids.txt --sequential

npm run process my-video-id # Single video npm run batch video1 video2 # Multiple videos npm run batch-file # From video-ids.txt file

video-tutorial-accessibility/ ├── cloudinary-video-ai-processing.js # Single video processor ├── batch-process-videos.js # Batch processor ├── video-ids.txt # List of video IDs to process ├── package.json # Project dependencies ├── .env.example # Environment template └── README.md # This file 

The script automatically generates transcripts in the following languages:

• 🇫🇷 French (France & Canada)
• 🇪🇸 Spanish
• 🇩🇪 German
• 🇵🇹 Portuguese (Portugal & Brazil)
• 🇮🇳 Hindi
• 🇯🇵 Japanese
• 🇨🇳 Chinese (Simplified)
• 🇻🇳 Vietnamese

For each processed video, Cloudinary will generate:

• {video-id}-chapters.vtt - Video chapters/timestamps
• {video-id}.transcript - Main transcript (original language)
• {video-id}.{language}.transcript - Translated transcripts

Example for video my-tutorial:

my-tutorial-chapters.vtt my-tutorial.transcript my-tutorial.fr-FR.transcript my-tutorial.es.transcript my-tutorial.de.transcript ... 

Add your video public IDs to video-ids.txt, one per line:

# Lines starting with # are comments video-1 folder/video-2 tutorials/advanced-video 

1. Missing dependencies:

   npm install

2. Invalid credentials:

   • Check your .env file
   • Verify credentials in Cloudinary Dashboard

3. Video not found:

   • Ensure video exists in your Cloudinary account
   • Include folder path if video is in a subfolder
   • Check video public ID spelling

4. API rate limits:

   • Use sequential processing for large batches
   • Reduce parallel processing concurrency

• Cloudinary Upload API
• Video Auto-Transcription
• Video Auto-Chaptering

1. Fork the repository
2. Create a feature branch: git checkout -b feature-name
3. Commit changes: git commit -am 'Add feature'
4. Push to branch: git push origin feature-name
5. Submit a pull request

This project is licensed under the ISC License - see the package.json file for details.

For issues and questions:

• Check the Cloudinary Documentation
• Review the troubleshooting section above
• Open an issue in this repository