CrySense AI
Launch Dashboard
IoT + TinyML research prototype

Understand Patterns.
Respond Faster.

Real-time AI-powered infant sound pattern monitoring — edge inference on an ESP32-S3, streamed to a calm parent dashboard.

CrySense AI is an experimental audio pattern recognition system. It does not diagnose medical conditions and cannot determine with certainty why a baby is crying.

Live pipeline

  1. Baby Sound
  2. AI Analysis
  3. Likely Pattern
  4. Parent Dashboard

🍼 Likely Hungry

Confidence 82% · end-to-end 440 ms

Built like a product, shaped by research

Real-Time Monitoring

Live status, confidence and latency updates the moment a sound pattern is detected.

Edge AI on ESP32-S3

TinyML inference runs on-device, so audio never has to leave the room to be classified.

Web Microphone Mode

Test and demo the whole pipeline from a browser before hardware is connected.

Firebase Cloud

Realtime Database sync for device state, events and settings, with per-user access.

Personalized Calibration

Measure the room's noise floor and tune sensitivity in a guided wizard.

AI Training Lab

Curate datasets, extract MFCC features, train and evaluate an experimental model.

Privacy Controls

Consent metadata on every sample, export your dataset, delete all cloud data.