diff --git a/README.md b/README.md index 6af5802..3cecef4 100644 --- a/README.md +++ b/README.md @@ -29,13 +29,28 @@ This is the early development and ideation phase. The repository will include pr - **Google Cloud Vision API** – (future integration) - **Text-to-Speech / Speech-to-Text APIs** – Accessibility tools +## Voice & Keyboard Controls + +Press s on the keyboard or say "scan" through your microphone to trigger scene analysis. + ## Getting Started > 🚧 **Work in Progress**: Only starter files and prototypes are included at this stage. +### Prerequisites + +Make sure you have the following before running the project: + +- **Python 3.10+** +- **pip** for installing Python packages +- **Stable Wi-Fi connection** (required for speech recognition and Gemini AI API) +- **Webcam access** (built-in or external webcam) +- **Microphone access** (for voice commands) + Clone the repository and install dependencies: ```bash git clone https://github.com/kaushav07/VisionMate.git cd VisionMate pip install -r requirements.txt +python main.py \ No newline at end of file