EdgeEcho: Lock Your Phone, Touch Grass, and Let Edge AI Identify the Wild

Description and use

EdgeEcho is an offline PWA that identifies 521 environmental sounds using local edge AI and TTS, enabling users to stay immersed in nature without a screen.

Problem

Outdoor enthusiasts need a way to identify environmental sounds without pulling out their phone or relying on cellular connectivity.

Outcome

EdgeEcho enables hikers and birdwatchers to identify wildlife sounds offline, preserving privacy and eliminating data‑transfer costs.

Workflow

• 1. Tap "Start Listening" in the EdgeEcho app.
• 2. Lock the phone and place it in the pocket.
• 3. Walk or hike; the app continuously records audio.
• 4. The TensorFlow.js YAMNet model processes the 16kHz mono buffer locally.
• 5. When a sound is classified, offline TTS speaks the result into the earbuds.
• 6. No visual dashboard is shown, keeping the user’s eyes on the environment.

Evidence

EdgeEcho is a 100% offline Progressive Web App (PWA) that uses local edge AI to identify 521 environmental sounds, such as specific bird calls or flowing water.

Source

It operates hands‑free. Users tap "Start Listening," lock their device, and receive text-to-speech audio alerts through their earbuds. There is no visual dashboard to monitor, forcing users to keep their eyes on the environment.

Source

The AI Stack: Google’s open-weight YAMNet model (3.7MB .tflite mobile architecture) executed via TensorFlow.js (@tensorflow/tfjs-tflite).

Source

Zero Connectivity / Air‑Gapped Use: Closed cloud APIs require active LTE/5G and fail on remote trails. Open‑weight models allow the app to function fully in airplane mode.

Source