Sorry if this question is not related with null-byte. But please kindly help me.
I want to build personal assistant with python for my computer. It should work offline and should be able to open other application of computer.
So how can i build my personal assistant?
Any tutorials please share it. Thank you.
11 Responses
Should it be speech-controlled or just text-controlled in a terminal?
what should it be able to do except starting applications?
should your assistant have something like a personality or should it just do what you're saying?
have a nice day :)
Thank you for commenting. :)
It should be speech-controlled and just do what i say.
honestly unless you've already invested a lot into learning how to code you cant just create your own jarvis...so what you need to do is start learning how to program in python first. take a look at the python scripting for the aspiring hacker series to start.
i had learned python and know how to code on python. As i am doing college project(some thing like professional first time). So i needed guide to crate my own personal assistant to submit on college.
I dont know really much about python and its functions (libs etc.)
But hopefully there is a speech input library or something like that, and then you just have to convert the "commands" (e.g. start iceweasel) into shell commands (/usr/bin/iceweasel) which then will be executed. I would do that with an text document containing something like a "key-value-collection" where you can add and extend the features. Like "start iceweasel;/usr/bin/iceweasel;shutdown; halt -h" and so on. you may format this file more nicely than i did ;)
to say short:
you could maybe also add some features like a name trigger, like "hey siri", "hey galaxy", "jarvis", "pi", ...
you should know at least one of them :D
Or some smalltalk functions with randomized answers
much more ideas, but no time to write xD cu
Thank you for great idea, and thank you for giving time and explaining this to me.
An Indian developer iis currently working on Jarvis.. the project as been divided into 3 parts.. Brain, Mouth and Ear. Google about that.
Yeah i have downloaded that project source code and am peeking on code.
Offline speech recognition pack is also available...
Anyway thanks for commenting bro. :)
Where is the code...
Share Your Thoughts