The Narakeet story
The Narakeet project came out of Gojko Adzic’s participation in 2018 Startup School (under the old name as Video Puppet). Here’s Gojko’s story about it:
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 picture 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 web page shown in the tutorial significantly changed, so the video had to be updated. 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 takes care of all the boring and time-consuming tasks of video editing, and lets authors focus on creating good content. It will automatically create video clips from images, align audio and video segments, add captions, display text on top of videos and apply transitions between scenes. It will record life-like narration using the latest neural text-to-speech systems, so the audio will be consistent no matter how many times you change the script. Narakeet makes it straightforward to create the first version of a video, and painless to update it in the future. It lets you edit videos as easily as editing text.
Although generated voice might not be for everyone, I found it amazingly good for iterations and experiments. Once you are happy with the content and the flow of the story, you can easily replace the generated narration with your own voice, or a professionally recorded audio. Narakeet will take care of synchronisation, so the picture aligns perfectly with your voice.
More information
Last updated