https://github.com/mr-yash-01/voiceassistant
A powerful Python-based desktop voice assistant that executes commands faster than Cortana, built using native libraries without relying on pre-trained AI models.
https://github.com/mr-yash-01/voiceassistant
ai-free automation cli-tools desktop-assistant python3 speech-recognition voice-assistant voice-commands
Last synced: 7 months ago
JSON representation
A powerful Python-based desktop voice assistant that executes commands faster than Cortana, built using native libraries without relying on pre-trained AI models.
- Host: GitHub
- URL: https://github.com/mr-yash-01/voiceassistant
- Owner: Mr-Yash-01
- Created: 2024-06-08T10:54:10.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-05-08T06:33:12.000Z (11 months ago)
- Last Synced: 2025-06-20T21:39:21.393Z (10 months ago)
- Topics: ai-free, automation, cli-tools, desktop-assistant, python3, speech-recognition, voice-assistant, voice-commands
- Language: Python
- Homepage:
- Size: 11.7 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🎙️ PyCommand: CLI-Based Desktop Voice Assistant
**PyCommand** is a fast and lightweight voice-controlled desktop assistant built entirely in Python. Unlike Cortana or other bulky assistants, PyCommand operates directly through your system’s command line to perform tasks like opening apps, files, or searching — all without any heavy pre-trained AI models.
---
## 🚀 Features
- 🎤 **Voice Command Execution**: Execute commands directly via voice input using your microphone.
- 🗂️ **Open Any File or App**: Launch files, folders, and applications just by saying their names.
- ⚡ **Faster than Cortana**: Lightweight execution makes it faster and more responsive.
- 💻 **Runs via Terminal**: No UI overhead — everything works from the CLI.
- 📦 **No Heavy AI Models**: Designed using native Python and speech libraries only.
- 🔊 **Text-to-Speech & Recognition**: Uses libraries like `speech_recognition` and `pyttsx3`.
---
## 🧠 Tech Stack
- **Programming Language**: Python
- **Voice Recognition**: `speech_recognition`, `pyttsx3`
- **OS Interaction**: `os`, `subprocess`, `platform`
- **Other Libraries**: `time`, `datetime`, `webbrowser`
---
## 🛠️ Getting Started
### 🔧 Requirements
Make sure Python is installed and run:
-pip install speechrecognition pyttsx3 pyaudio
# ▶️ Run the Assistant
- python pycommand.py
You’ll be prompted to speak your command — the assistant will then process and act accordingly.
## 🧪 Example Voice Commands
- "Open Chrome"
- "Play music"
- "Open project folder"
- "Search Python tutorial on YouTube"
## 📁 Folder Structure
pycommand/
- ├── pycommand.py
- ├── requirements.txt
- └── README.md