Monthly Archives: December 2016

Jasper Image v1.6 – Coming Soon!

There are already several improvements to the image, and I have put out feelers for any fixes/updates/etc that I can do to make the user experience better.  I already have a few of the obvious ones, however please feel free to report them in the new slack room “image-v1-6”, or in the Forums at the following LINK.

I am already working on it being pre-installed in the future with a REST api on it.  Making it easy to integrate with anything!

I will be posting the release notes with the new updates with the new image, and here as a post.  So please keep an eye out.



How AI listens in Jasper (and others)!

 There are two basic kinds of listeners, an active and a passive.  You will not get good offline (passive listener) results for a wide variety of speech currently.  Most offline listeners are used as ‘passive’ listeners. They usually just listen for the wake word or just a few small commands.  They are very accurate but can’t sustain a large vocabulary without CPU issues.  Some are also closed source such as (snowboy), and require that you train each word on their site.

The other kind, aka the “Active listener”; or the one always listening.  Would be used to listen once activated by the passive listener, and has a much more broad vocabulary.  However, these are online only. Due to the way they work (gathering metadata to increase accuracy), its just not possible currently on a small device. Examples would be standard APIs such as Google,, Ivona/Polly, etc.

There are projects to fix these offline issues, but they are all in the works. See my site for info on some of them.