A fast, versatile voice assistance that can handle daily tasks seemlessly.
- Completely written in python.
- Uses
genai api
to implement Gemini Pro. - Implemented
Speech Recognition Python Library
for voice recongition. - Used API of several different services.
$ git clone https://github.com/ananyab1909/Nova-voice-assistant.git
- clone this project to your computer.$ cd Nova-voice-assistant
- go inside the project directory.- Run
pip install -r ./requirement.txt
to setup dependencies and virtual environment. python ./main.py
to execute the python file.- To deactivate the virtual environment, run
deactivate
.
- Gemini API for implementing generative AI.
- Spotify API for playing music.
- WhatsApp API for handsfree messaging.
- Openweather API for realtime weather forecasts.
- API keys for Openweather and Gemini.
- A new application on the spotify developer portal, and the client id, client secret and redirect uri.
- WhatsApp Web must be logged in on default browser for Nova to access it
Hello, my name is Ananya Biswas. I am an Engineering Student at Kalinga Institute of Industrial Technology. I enjoy making teeny tiny projects in my leisure time and this is one of them. Now that my this project is over, I am open-sourcing the project. Hope you like it!
Lastly, I would like to put it out there that I have worked on other projects that you may like. You can check them out at my Github. Give it a whirl and let me know your thoughts.
If you would like to contribute to this project, you can do so by creating a PR ; and to support my work, you can click on the projects you like and reward a star.
- Ananya Biswas(Me)
- Github : https://github.com/ananyab1909/
- Instagram: https://instagram.com/thegraffiti.mind