Taylor Smith

Author Archives: Taylor Smith

Un experimento rápido: translating Cloudflare Stream captions with Workers AI

Cloudflare Stream launched AI-powered automated captions to transcribe English in on-demand videos in March 2024. Customers' immediate next questions were about other languages — both transcribing audio from other languages, and translating captions to make subtitles for other languages. As the Stream Product Manager, I've thought a lot about how we might tackle these, but I wondered…

What if I just translated a generated VTT (caption file)? Can we do that? I hoped to use Workers AI to conduct a quick experiment to learn more about the problem space, challenges we may find, and what platform capabilities we can leverage.

There is a sample translator demo in Workers documentation that uses the “m2m100-1.2b” Many-to-Many multilingual translation model to translate short input strings. I decided to start there and try using it to translate some of the English captions in my Stream library into Spanish.

Selecting test content

I started with my short demo video announcing the transcription feature. I wanted a Worker that could read the VTT captions file from Stream, isolate the text content, and run it through the model as-is.

The first step was parsing the input. A VTT file is a text file that Continue reading

Cloudflare Stream Low-Latency HLS support now in Open Beta

Cloudflare Stream Low-Latency HLS support now in Open Beta
Cloudflare Stream Low-Latency HLS support now in Open Beta

Stream Live lets users easily scale their live-streaming apps and websites to millions of creators and concurrent viewers while focusing on the content rather than the infrastructure — Stream manages codecs, protocols, and bit rate automatically.

For Speed Week this year, we introduced a closed beta of Low-Latency HTTP Live Streaming (LL-HLS), which builds upon the high-quality, feature-rich HTTP Live Streaming (HLS) protocol. Lower latency brings creators even closer to their viewers, empowering customers to build more interactive features like chat and enabling the use of live-streaming in more time-sensitive applications like live e-learning, sports, gaming, and events.

Today, in celebration of Birthday Week, we’re opening this beta to all customers with even lower latency. With LL-HLS, you can deliver video to your audience faster, reducing the latency a viewer may experience on their player to as little as three seconds. Low Latency streaming is priced the same way, too: $1 per 1,000 minutes delivered, with zero extra charges for encoding or bandwidth.

Broadcast with latency as low as three seconds.

LL-HLS is an extension of the HLS standard that allows us to reduce glass-to-glass latency — the time between something happening on the broadcast end and a user seeing Continue reading

Introducing Low-Latency HLS Support for Cloudflare Stream

Introducing Low-Latency HLS Support for Cloudflare Stream
Introducing Low-Latency HLS Support for Cloudflare Stream

Stream Live lets users easily scale their live streaming apps and websites to millions of creators and concurrent viewers without having to worry about bandwidth costs or purchasing hardware for real-time encoding at scale. Stream Live lets users focus on the content rather than the infrastructure — taking care of the codecs, protocols, and bitrate automatically. When we launched Stream Live last year, we focused on bringing high quality, feature-rich streaming to websites and applications with HTTP Live Streaming (HLS).

Today, we're excited to introduce support for Low-Latency HTTP Live Streaming (LL-HLS) in a closed beta, offering you an even faster streaming experience. LL-HLS will reduce the latency a viewer may experience on their player from highs of around 30 seconds to less than 10 in many cases. Lower latency brings creators even closer to their viewers, empowering customers to build more interactive features like Q&A or chat and enabling the use of live streaming in more time-sensitive applications like sports, gaming, and live events.

Broadcast with less than 10-second latency

LL-HLS is an extension of HLS and allows us to reduce glass-to-glass latency — the time between something happening on the broadcast end and a user seeing it on Continue reading