Cloudflare adds the ability to create AI-generated captions for on-demand videos and recordings of live streams
Cloudflare is introducing AI-generated captions for on-demand videos and recordings of live streams to its Stream platform.
As part of Cloudflare’s mission to help build a better Internet, this feature is available to all Stream customers at no additional cost, according to the company.
This solution is designed for simplicity, eliminating the need for third-party transcription services and complex workflows.
With Stream’s integrated solution, the caption generation process is seamlessly integrated into the existing video management workflow, saving time and resources. Regardless of when a video is uploaded, you can easily add automatic captions to enhance accessibility. Captions can now be generated within the Cloudflare Dashboard or via an API request, all within the familiar and unified Stream platform, according to the vendor.
This feature is designed with utmost consideration for privacy and data protection. Unlike other third-party transcription services that may share content with external entities, data remains securely within Cloudflare's ecosystem throughout the caption generation process. Cloudflare does not utilize your content for model training purposes, the vendor said.
The Stream engineering team built this new feature using Workers AI, allowing the company to access the Whisper model—an open source Automatic Speech Recognition model—with a single API call.
Using Workers AI radically simplified the AI model deployment, integration, and scaling with an out-of-the-box solution.
Not only does Workers AI solve the pain of managing underlying infrastructure, it also automatically scales as needed.
To optimize processing speed, Cloudflare’s team parallelized as many operations as possible. By concurrently creating the 30-second audio batches and sending requests to Workers AI, the company takes full advantage of the scalability of the Workers AI platform. Doing this greatly reduces the time it takes to generate captions but adds some additional complexity.
In the future, the company will be focused on adding more languages and supporting longer videos.
For more information about this news, visit www.cloudflare.com.