I decided to publish the code for my python voice assistant on github. Here's the link.
To run it, you need to install the following modules:
- speech_recognition
- pygame
- wolframalpha
- wikipedia
- pyvona
- pyperclip
- webbrowser - should be part of the python core packages
If you look into the code you can really grasp the power of working with APIs. What I did was just to put things together like lego bricks.
The voice recognition engine relies on Google's API, while the natural voice synthesizer is Amazon's Ivona. Wolfram and Wikipedia are the giants behind the results.
I remember working at this code for a couple of weeks at the beginning of this past summer. I usually did it at night and it was extremely taxing on my nervous system; hours would go by without me even noticing it. I remember that to lay off the steam and take myself out of the intensity, I would get into my car and drive aimlessly at small hours in the AM...
Anyhow, it may appear obvious that there's a lot of improvement to be done. Many features can be added and I'm not sure how much time I will further devote to this as I am currently immersed in other projects. If you decide to try it, if you have ideas, and if you need help with this, do let me know!
To stay in touch with me, follow @cristi
Cristi Vlad, Self-Experimenter and Author
Congrats, that's neat. Siri/Alexa-on-demand sort of stuff...
with full dedication and a few months' worth of work, this could be turned into a decent assistant :)