A Speech Assistant Python program that converts speech to text and vice versa, thus enabling it to convert user voice requests, parse them and respond in real-time. Has optional GUI.
Report Bug
·
Request Feature
This is a Python program that uses SpeechRecognition and pyttsx modules to recognize user speech, convert it into text, parse it, and then produce speech output. It simulates the behaviour of a speech assistant.
This project is entirely built with the following components and languages:
To get a local copy of the program up and running follow these simple steps.
Python>=3.7 and pip>=19.2 should be installed. After installation, check their versions using
python --version
pip --version
- Clone the repo
git clone https://github.com/vijethph/violet-speech.git
- Open the downloaded folder
cd violet-speech
- Install the packages listed in
requirements.txt
using the following command:
pip install -r requirements.txt
- Finally run the program using
python main.py
You can also try the Graphical User Interface(GUI) version of it by running following command:
python gui.py
Simply ask anything when the speech assistant introduces itself. You can ask its name, current time, location of a place, or ask to perform a Google search.
Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature
) - Commit your Changes (
git commit -m 'Add some AmazingFeature'
) - Push to the Branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
Distributed under the GNU GPL License.
Vijeth P H - @vijethph
Project Link: https://github.com/vijethph/violet-speech
Made with ❤ in India.
If you like this project, please ⭐ this repo and share it with others 👍