Product builders around the globe often trade-off between three methods
When must you (re)-build your fashions and put money into iteration to get nice high quality? When must you borrow high-performance APIs and free your builders to make the subsequent large factor? And when must you purchase options to your downside?
VideoKen is an AI-powered video interactivity answer that transforms studying movies into interactive and immersive experiences. On this age, consideration is at a premium, and learners have entry to extra info than they will devour. “VideoKen’s objective is to take learner engagement to the subsequent degree by making it simple for folks to find and work together with movies,” says Vishnu. VideoKen affords automated video chaptering, in-video quizzes, deep video search, video analytics, closed captioning, video internet hosting and different options to make this interplay wealthy and impactful.
What occurs behind the scenes at VideoKen?
VideoKen’s answer makes use of AI to trace, predict and enhance learner engagement utilizing in-video interactivity and actionable insights. The purpose is to reduce the issue of poor engagement amongst learners.
Over 100+ studying leaders leverage VideoKen to assist learners have interaction and work together with movies utilizing an auto-generated navigable storyline, deep video search and in-video assessments. These leaders additionally faucet into VideoKen’s in-depth analytics to realize insights into their learners’ preferences and conduct, which is used to optimize and prioritize their studying content material.
“VideoKen’s clients have been profitable by driving 3x extra engagement and retention on their studying movies,” in response to Vishnu.
VideoKen’s improvement journey
VideoKen’s journey began by creating in-house expertise (now patented) for bettering engagement. On high of their 5 patents, VideoKen wanted to have the ability to provide a complete answer to satisfy rising buyer wants. “The engineers have been keen to construct in-house fashions, nevertheless it turned out we couldn’t do all of it by ourselves,” says Vishnu.
Furthermore, VideoKen wanted an satisfactory cloud computing infrastructure which led to exploring and experimenting with varied choices earlier than selecting Azure.
Creating in-house machine studying fashions for speech-to-text transcription
Jeril Sebastian, Head of Engineering at VideoKen, shared insights on utilizing a few of the utilized AI providers. “Most of our providers depend on VideoKen’s personal AI expertise. One factor that we do depend on externally, is Azure’s Cognitive Providers for transcribing movies.”
Jeril defined that earlier than leveraging Microsoft Azure and its Cognitive Providers, VideoKen was utilizing a mix of its proprietary speech engine together with some providers of one other cloud supplier. “It was taking over a variety of time and wasn’t possible for us to pursue this method long-term,” Jeril mentioned, including that the corporate was spending twice as a lot cash on the in-house mannequin in comparison with Azure’s speech API. “Despite the fact that the whole lot was working effectively with our AI speech-to-text answer, we wanted to deal with our key strengths and have our builders work on options which are essential to our clients.”
After discovering that internet hosting GPU situations and coaching fashions in-house was taking over too many sources, VideoKen determined to check totally different choices, with Azure’s speech to textual content proving an ideal match. “Speech to textual content is a single constructing block of a a lot greater infrastructure, so we couldn’t afford to lose a variety of time and power, regardless of being happy with the general efficiency of our home-grown expertise. Subsequently, changing it with Azure was essentially the most logical step for us.”
VideoKen’s journey post-Utilized AI
Video transcription has develop into a norm these days. One of the vital essential features of creating movies extra immersive is making certain that learners don’t miss any essential info. Having realized Azure Cognitive Providers’ energy, Jeril and the engineering workforce managed to chop the price of video transcription by 50%.
“We used to have an ML engineer simply to coach the mannequin, enhance it, run the GPU situations, and so forth,” Jeril mentioned. “This was a full-time job for one individual, and now it takes only a few hours per week for me to maintain that total pipeline. Our ML engineer now has extra time to deal with researching and upgrading different providers provided by VideoKen, as a substitute of doing the grunt work to maintain our in-house transcription mannequin aggressive.”
Processing 1000’s of movies with Azure
Aside from Cognitive Providers, VideoKen additionally depends on different Azure advantages. “We use two particular items of expertise. One known as Azure Capabilities, and the opposite is Azure Container Situations,” defined Jeril. He added that the 2 tech items allowed VideoKen to scale up and down elastically, “We get 1000’s of movies at a time from our clients, so fast scalability is important.”
By counting on Azure Container Situations and Azure Capabilities, VideoKen has managed to arrange a pipeline which allowed the corporate to scale. “When there aren’t any movies to course of (theoretically), it prices us nothing,” Jeril mentioned. “However, when there are millions of movies coming in, VideoKen scales up routinely and is ready to deal with that load.” At full capability, VideoKen can course of roughly a thousand hours of video per day.
Jeril shared his pleasure with Capabilities and Container Situations. “I actually take pleasure in working with Capabilities, because it has saved us a variety of time. It is a realm of expertise known as serverless, and it has made administration and upkeep very easy.” Furthermore, Jeril acknowledged that Container Situations helped VideoKen’s scalability in a singular method, on condition that such expertise doesn’t exist on different cloud providers.
The long run seems vivid for VideoKen’s partnership with Microsoft, “Proper now, we’re proud of Azure, and the plan is to stick with the service for a very long time,” mentioned Jeril.
He expressed his satisfaction with Azure’s transparency concerning prices. “They’re making an attempt their greatest to indicate precisely how and the place our cash is spent for Azure’s providers. At any time when I go to the price administration part, I can see precisely the place we’re spending cash and the way a lot is being spent.” The primary benefit of this, in response to VideoKen’s Head of Engineering, is that the corporate could make higher choices on tips on how to use the Azure funds.
To get began with Microsoft for Startups Founders Hub, join right here.