Gojko Adzic is a partner at Neuri Consulting LLP. He one of the 2019 AWS Serverless Heroes, the winner of the 2016 European Software Testing Outstanding Achievement Award, and the 2011 Most Influential Agile Testing Professional Award. Gojko’s book Specification by Example won the Jolt Award for the best book of 2012, and his blog won the UK Agile Award for the best online publication in 2010. Gojko previously co-founded MindMup, a collaboration tool used by millions of schoolchildren worldwide to visualize ideas.
In this conversation, Gojko talks about his Narakeet product, that lets you convert a PowerPoint or another presentation to a voice-enabled video.
Geetesh: Gojko, can you tell us what motivated you to create Narakeet?
Gojko: A while ago, I wanted to make a video tutorial for an opensource tool. Coming up with the content was easy and fun. The rest of the experience was horribly frustrating. Aligning pictures with sound felt like a huge waste of time. Recording narration was even worse. It took me seven attempts to do a single paragraph without mistakes. It still sounded bad, so I gave up and paid a professional voice artist. Her voice was great, but she spoke slower than me, so I had to re-edit the video again. It took more than four hours of effort to create just five minutes of good content.
Six months later, a webpage shown in the tutorial changed significantly, so I had to update the video. Instead of a simple tweak, it all came crashing down. I foolishly tried to save money by asking the artist to record just the changed part. Same person, same equipment, but you could clearly hear the difference. I had to choose between a video that sounded inconsistent, or paying for the whole thing again and wasting time on re-aligning everything. There had to be a better way of making videos, but couldn’t find any, so I decided to build it. And that’s how Narakeet came to be. It now takes me ten to fifteen minutes to make a great five-minute video, not hours like before.
Narakeet makes it easy to turn PowerPoint slides to narrated videos. In brief, it uses artificial intelligence to create life-like narration from speaker notes. Users can edit video as simply as they would edit text, saving hours by not having to record and re-record audio, synchronize pictures with sound and transcribe subtitles.
Geetesh: How does one get started with using Narakeet? Are there any resources or best practices you recommend?
Gojko: Getting started is easy. Just make a PowerPoint presentation and type the narration text into the speaker notes in each slide. Then go to Narakeet and click the big blue “Create a video now” button. Select the presentation type, upload your file, and in a few moments, you’ll be able to choose the video size, language, and voice. It was created for a global audience and supports 20 languages and counting, with more than 100 voices.
The home page also has four good demos for typical use cases, such as remote lectures, marketing/promotional videos, and quizzes. You can just download one of those presentations to see how the video was made, tweak it, and upload it again to make a new video. For me, that’s one of the best things about Narakeet. If you want to tweak something or fix a mistake, just edit the script and upload the presentation again. Narakeet will just generate the new narration and align everything. No need for you to waste time on readjusting everything again.
For people that want to experiment a bit more, we have five very easy lessons online that teach users how to create more engaging dialog, control pauses in narration, and tell Narakeet to use some specific pronunciation (for example, for scientific terms). You can check them all out at our PowerPoint to Video page.