{"id":38449,"date":"2025-09-10T07:00:00","date_gmt":"2025-09-10T14:00:00","guid":{"rendered":"https:\/\/cloudinary.com\/blog\/?p=38449"},"modified":"2025-09-05T11:56:30","modified_gmt":"2025-09-05T18:56:30","slug":"making-videos-accessible-at-scale-using-ai","status":"publish","type":"post","link":"https:\/\/cloudinary.com\/blog\/making-videos-accessible-at-scale-using-ai","title":{"rendered":"Making Videos Accessible at Scale Using AI"},"content":{"rendered":"

I\u2019ve recently been learning about web accessibility in order to write the Accessible Media guide<\/a> in the Cloudinary docs. The guide focuses on how to make use of Cloudinary functionality to help make the images and videos on your website accessible to everyone. This means adding alternative text to images, captions to videos, considering the use of colors, animations, and much more.<\/p>\n

In our docs, we have well over 100 video tutorials, with more being added at an unrelenting pace. A few of these already had captions, but most didn\u2019t, so it was about time we practiced what we preached and made our own videos accessible.<\/p>\n

Cloudinary\u2019s AI-powered features make video accessibility achievable at scale. The Cloudinary transcription service<\/a> automatically creates transcripts from videos using advanced AI, which can be used for captions, and has the added benefit of offering AI-powered translations and enabling auto-chaptering. Translations are great for engaging wider, global audiences, and chaptering can help viewers and screen readers navigate through your videos more easily. So, in addition to adding captions, I decided to leverage these AI capabilities to add these features at the same time.<\/p>\n

Due to the number of videos, manual processing wasn\u2019t feasible. Fortunately, Cloudinary\u2019s AI automation made it possible to process our entire video library efficiently.<\/p>\n

A Scripted Approach<\/h2>\n

To leverage Cloudinary\u2019s AI-powered accessibility features across our video library, I needed to create a solution that would invoke transcription, translation, and auto-chaptering on a list of videos, referenced by their public IDs. The implementation called for transcription and translation in multiple languages, including different flavors of French and Portuguese, Spanish, German, Hindi, Japanese, Chinese, and Vietnamese.<\/p>\n

The solution, a vibe-coded node.js script, processes multiple videos efficiently and can be found here: https:\/\/github.com\/cloudinary-devs\/video-tutorial-accessibility<\/a>.<\/p>\n

The key part is the call to the explicit<\/code> method of the Upload API to trigger Cloudinary\u2019s AI processing:<\/p>\n

const<\/span> result = await<\/span> cloudinary.uploader.explicit(publicId, explicitOptions);\n<\/code><\/span>Code language:<\/span> JavaScript<\/span> (<\/span>javascript<\/span>)<\/span><\/small><\/pre>\n
Where the explicitOptions are defined as:<\/p>\n
   const<\/span> explicitOptions = {\n      resource_type<\/span>: 'video'<\/span>,\n      type<\/span>: options.type || 'upload'<\/span>,\n      \n      \/\/ Enable automatic chaptering<\/span>\n      auto_chaptering<\/span>: true<\/span>,\n      \n      \/\/ Enable automatic transcription with translations<\/span>\n      auto_transcription<\/span>: {\n        translate<\/span>: TRANSLATION_LANGUAGES\n      },\n      \n      \/\/ Optional: Invalidate cached versions<\/span>\n      invalidate<\/span>: options.invalidate || false<\/span>,\n      \n      \/\/ Optional: Notification URL for completion webhook<\/span>\n      ...(options.notification_url && { notification_url<\/span>: options.notification_url })\n    };\n<\/code><\/span>Code language:<\/span> JavaScript<\/span> (<\/span>javascript<\/span>)<\/span><\/small><\/pre>\n
Auto-chaptering is activated simply by setting the auto_chaptering<\/code> parameter to true<\/code>. The AI analyzes the video content to automatically identify natural break points and create meaningful chapter divisions.<\/p>\n
Auto-transcription and translation is invoked by setting the translate parameter of the auto_transcription<\/code> option to an array of languages, defined as follows:<\/p>\n
\/\/ Translation languages as specified<\/span>\nconst<\/span> TRANSLATION_LANGUAGES = [\n  'fr-FR'<\/span>,  \/\/ French (France)<\/span>\n  'fr-CA'<\/span>,  \/\/ French (Canada) <\/span>\n  'es'<\/span>,     \/\/ Spanish<\/span>\n  'de'<\/span>,     \/\/ German<\/span>\n  'pt-PT'<\/span>,  \/\/ Portuguese (Portugal)<\/span>\n  'pt-BR'<\/span>,  \/\/ Portuguese (Brazil)<\/span>\n  'hi'<\/span>,     \/\/ Hindi<\/span>\n  'ja'<\/span>,     \/\/ Japanese<\/span>\n  'zh-CN'<\/span>,  \/\/ Chinese (Simplified)<\/span>\n  'vi'<\/span>      \/\/ Vietnamese<\/span>\n];\n<\/code><\/span>Code language:<\/span> JavaScript<\/span> (<\/span>javascript<\/span>)<\/span><\/small><\/pre>\n
If you only want transcription, without translation, just set auto_transcription<\/code> to true<\/code>.<\/p>\n
So, with the script set up, I simply had to specify the public IDs of the videos I wanted to process in video-ids.txt<\/a>.<\/p>\n
After running the script, each video now had a set of files associated with it:<\/p>\n
Translation requires you to have a subscription to the Google Translation add-on<\/a>. You can register for the free tier<\/a> in the Cloudinary Console.<\/p>\n