Personal Voice Assistant using Python - Mily

This is a project to build an AI voice assistant using Python. The Voice assistant interacts with the user to perform several tasks.

About Mily :

Mily is an AI personal voice assistant service built using Python. It can understand human speech and perform basic tasks requested by the user.

When the user specify the appropriate trigger words, the asistant will execute the user's command.

Please see below for some of the tasks that this voice assistant can perform:

1. Get the weather of different cities

    User: Hey Mily, tell me the weather
   

2. Open question

    User: Hey Mily, I have a question
   

3. Translator

    User: Translate for me
   

4. Top 5 headlines in US

    User: Hey Mily, tell me the news
   

5. Stock price

    User: Hey Mily, tell me the Tesla stock price
   

6. Ask geographical and computational questions

    Human: Hey G-One, What is the capital of California? / Hey G-One what is Sin 90?
   

Running on native machine

Dependencies

• python3
• portaudio (for recording with pyaudio to work)
• ctcdecode - for speechrecognition

If you're on mac you can install portaudio using homebrew

NOTICE: If you are using windows, some things may not work. For example, torchaudio. I suggest trying this on linux or mac, or use wsl2 on windows

using virtualenv (recommend)

1. virtualenv voiceassistant.venv
2. source voiceassistant.venv/bin/activate

pip packages

pip install -r requirements.txt

In-Built libraries required to be imported:

1.os

2.datetime

3.web browser

4.subprocess

Mily uses third party APIs to predict weather in different cities and to ask computational and geographical questions. Free API keys can be generated by creating an account in the following applications.

Open Weather Map - To forecast weather

WolframAlpha - To answer questions

Enjoy =)