A real-time AI tool that translates American Sign Language (ASL) into spoken words using your laptop camera, empowering seamless communication for the deaf and hard-of-hearing community. Bridging the gap between gestures and spoken language, silently.
Real-time ASL Recognition: Processes hand signs via webcam at 15-30 FPS
Custom Neural Network: Lightweight CNN architecture optimized for ASL alphabet
Text-to-Speech: Instant vocal output using pyttsx3 (offline) or Google TTS (online)
Cross-Platform: Works on Windows, macOS, and Linux
Privacy-First: No cloud dependency—all processing happens locally