This project is a voice assistant that takes voice input using the Google Speech Recognition API. The voice input is then processed, and an action is decided based on the user's command. The available actions include searching on Google, playing a video on YouTube, calculating something, and opening an application. The project uses Selenium to automate tasks done using web browsers, the os library to open applications within the system, and the Wolfram API to perform calculations. The project also uses a text-to-speech engine to answer in voice mode.
To use the voice assistant, you need to have Python 3 installed, along with the following libraries:
- SpeechRecognition
- selenium
- pyaudio
- pyttsx3
- wolframalpha
- os
To use the voice assistant, run the main.py file. The assistant will listen for a voice command and perform an action based on the command. You can speak commands like "search on Google for pizza", "play a video on YouTube", "calculate 2 plus 2", or "open Notepad".
This project is a voice assistant that can perform various actions based on the user's voice command. The project uses the Google Speech Recognition API to listen to voice input and then processes it to decide on an action. The available actions include searching on Google, playing a video on YouTube, calculating something, and opening an application. The project uses various libraries like Selenium, PyAudio, pyttsx3, and WolframAlpha to perform different tasks. The project also uses a text-to-speech engine to answer in voice mode. The project can be further extended to add more actions and improve its functionality.