Important notice the project is dead because my gcp credits expired :(
Ava stands for Advanced Voice Assitant. Her mission in life is simple it is to help me with my daily tasks. Currently, she is running on my computer and only responds to my voice and the voice of my parents. She is still in production mode there will updates that will come along the way.
Here are how Ava works and the packages it uses,
-
speech_recognition
Ava uses speech_recognition to detect voices. Ava uses a python package called speech_recognition. It is a popular speech recognition package, and I recommend using this package if you want to build your own AI Bot -
natural language processing
Ava uses the google cloud natural language API to find the entity and sentiment. It is beneficial because you don't want to hard code all of the commands.
Authentication
Before you can talk with AVA, she needs to know that if it's me (Shashank) so it sends an email to my inbox with a verification code, which s randomly generated. If my response is equal to the verification code, then it will speak. This feature is cool because I don't want strangers to gain access.
21 March - Mark 1 Release Notes
I want to keep this repository open-source. I want people to contribute to this repo because I want people to have this tool as a reference if they are building their own AI system that will help them in their lives.
(Don't read this if you know open source works) Here are the steps for beginners who don't know how open source works
- Fork it (https://github.com/shashanke7y/ava/fork)
- Create your feature branch (git checkout -b feature/fooBar)
- Commit your changes (git commit -am 'Add some fooBar')
- Push to the branch (git push origin feature/fooBar)
- Create a new Pull Request