The same AI running on this land runs right here, in your browser. Hold the button and let it listen.
A live demo of the on-device model. It listens for a fixed set of local wildlife, so everyday sounds (voices, TV, traffic) may get a low-confidence guess. A real Still Habitat ear is tuned to your land.
An uncommon visitor one of the ears on this land picked up recently.
Every species the ears here have identified, most-heard first.
Your land, your model. No servers to run, no audio leaving the property.
An ear records around the clock and identifies species right on the device with a model trained on your own land — no audio ever leaves the property.
Only the result — the species and a confidence — is published to this page. No recordings, no locations. It updates the moment a bird sings.
Place more ears anywhere on the land. Each one listens and identifies on its own — coverage grows, the model keeps learning your place.
Which species rule the daylight hours — and which come alive after dark.
Detection intensity by hour across the most heard species — darkest cells are peak activity.
The land wakes up in a particular order.
Every species heard here is logged by an ear — a small, low-power listener that identifies wildlife on-device, around the clock, with a model trained on your own land. No cameras, no recordings leave the property, just acoustics. The busiest hour is the dawn chorus, when the night's silence gives way to a wall of sound.
Notes left by guests who stayed and listened.