Inspiration
What it does
PulseSurveillant listens to short voice clips (recorded through our web interface), analyzes the user's emotion and checks for banned or harmful phrases (e.g., "I hate", "slave", etc.). It evaluates the severity using an AI-generated confidence score, and sends a wireless signal to our ESP32-controlled device to activate a physical response.
How we built it
Challenges we ran into
Learning from zero about incorporating API build up websocket and debugging debugging voltage device
Accomplishments that we're proud of
Turning our dreams into a physical working prototype -- we successfully built the full pipeline, implemented a real-time feedback mechanism, and integrated multiple technologies (Gemini, Elevenlabs, WebSockets, ESP32) in under 24 hours.
What we learned
What's next for PulseGuard
Deploy the system for real-world use cases like stress monitoring, burnout detection, etc. Central monitoring system for a manager to administer motivation directly and have multiple connections Consistent and controllable. Currently the high voltage module is missing a piece that makes it so that it varies between a light tickle to very Painful personalized profile&history Miniaturization and power supply
Built With
- 98.css
- elevenlabs
- gemini
- javascript
- python
Log in or sign up for Devpost to join the conversation.