https://github.com/hrutavmodha/desktop-assistant
A smart voice assistant application made using HTML, CSS, JS Node.js and Python
https://github.com/hrutavmodha/desktop-assistant
css html javascript nltk python react sk-learn tailwind-css voice-assistant webapp
Last synced: about 1 month ago
JSON representation
A smart voice assistant application made using HTML, CSS, JS Node.js and Python
- Host: GitHub
- URL: https://github.com/hrutavmodha/desktop-assistant
- Owner: hrutavmodha
- License: mit
- Created: 2025-06-09T07:07:55.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-25T14:34:05.000Z (12 months ago)
- Last Synced: 2025-06-25T15:33:56.820Z (12 months ago)
- Topics: css, html, javascript, nltk, python, react, sk-learn, tailwind-css, voice-assistant, webapp
- Language: JavaScript
- Homepage:
- Size: 518 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
Awesome Lists containing this project
README
# 🧠 Voice-Assistant
- Voice-Assistant is a **ML-based Voice Assistant**
- This is a desktop-based voice assistant powered by the ML model, which is built using Python.
- The UI is built using Electron.js while inference is done by using Node.js.
- It understands your speech, processes it using a custom-trained intent recognition model and executes platform-specific commands.
---
# 🚀 Features
- 🎙️ Voice Input
- 🤖 ML-based Intent Detection
- ⚙️ Cross-platform Command Execution
- 🗣️ Voice Output
- 🖥️ Desktop-first App
- 🔐 Privacy-Focused
---
# 🏗️ Tech Stack
| Layer | Stack |
|---------------|------------------------------------|
| Frontend | HTML, CSS, JS and React.js |
| Backend | Node.js and Python |
| Model | Sci-kit Learn ML models |
| Voice I/O | Web Speech API |
---
# 🧠 How It Works
1. 🎙️ User speaks a command
2. 🎧 Voice is transcribed and sent to Python backend
3. 🧠 The ML model classifies intent
4. 💻 Executes the platform-specific command
5. 🗣️ Response is spoken back to the user alongwith the execution of the task
---
# 🔁 Requirements
- Node.js & npm
- Python & pip
- Electron.js & React
---
# 🛠️ Run Locally
## 1. Clone the repository
```Bash
git clone "https://github.com/hrutavmodha/voice-assistant.git"
cd ./voice-assistant
```
## 2. Train the models
```Bash
cd ./backend/model/model1
python ./train.py
cd ../model2 && python ./train.py
cd ../model3 && python ./train.py
cd ../model4 && python ./train.py
```
## 3. Install dependencies
```Bash
cd ..
npm install
pip install sklearn joblib
cd ../frontend
npm install
cd ..
npm install
cd backend
```
## 4. Start the main server
```Bash
npm run start
```
## 5. Start the voice assistant's server
```Bash
python -m frontend.chat.app
```
---
# 👨💻 Author
Made with passion by **Hrutav Modha**
---
# 📌 Note
- After running the app.py, wait for some time, the browser will also get opened automatically at the URL http://localhost:3000
- This project is purely offline and does **not rely on any of the external APIs and nor it is dumb `if-elif-else`-like rule-based voice-assistant**
- It’s a fully local voice assistant with a custom-trained AI model, which is designed with keeping privacy in mind.