Meet SoundSpotter — Teach your phone the doorbell

Lifestyle

SoundSpotter

Teach your phone the doorbell.

What SoundSpotter does

SoundSpotter is the offline custom sound recognition app for the 37.5 million Americans with hearing trouble — and for anyone whose phone can't recognize their specific doorbell, oven timer, dog's whine, or smoke alarm.

Apple's built-in Sound Recognition is great but limited. You can't add an arbitrary sound. Custom training (electronic alarms only) routinely fails — Apple Community threads document waits of 12+ hours with no result. There is no event log, so you can't review what the phone heard while you were in the shower or asleep.

SoundSpotter fixes all three gaps:

— Train any sound in 30 seconds. Tap Record. Hold the phone near the sound (your doorbell, your microwave beep, your cat's distinct meow at 5am). The app captures 5 samples and trains an on-device CoreML classifier using SoundAnalysis transfer learning. No server. No cloud. — Per-sound haptic patterns. Doorbell = three short pulses. Oven = one long. Smoke alarm = SOS. CoreHaptics fires exactly the pattern you want. — Persistent event log. Every recognized sound is timestamped and saved. Scroll back: 'the oven beeped at 7:14pm; the dog whined at 3:02am.' — Background listening. BackgroundTasks keeps the classifier alive when the app is closed. — No mic data leaves the phone. The model lives in the app's sandbox. The audio is never recorded — only the classifier output (timestamp + label) ever gets stored.

For the deaf, hard-of-hearing, and the very-curious — the sound recognition Apple should ship.

A look inside

Tap any screenshot to open the full-resolution version.

What's inside

• Sound library — List of trained sounds with name, sample count, last-fired timestamp
• Train new — Record 5 samples of a sound; SoundAnalysis transfer learning on-device
• Live listen — Real-time classifier; haptic + on-screen indicator when sound detected
• Event log — Chronological list of every detection across all sounds
• Haptic patterns — Per-sound vibration pattern editor (short/long/SOS)

Why we built it

Apple's built-in Sound Recognition can't be expanded to arbitrary sounds, custom training fails silently, and there's no event log — so DHH users can't review what their phone 'heard' while they were in the shower or asleep.

What makes it different

SoundSpotter is the only iOS app that lets users train an arbitrary custom sound classifier in 30 seconds on-device using CoreML + SoundAnalysis transfer learning, fires per-sound CoreHaptics patterns, and persists a timestamped event log — Apple's built-in is restricted to a preset list, Ava and Otter handle speech o…

Who it's for

Hobbyists who want a tool that respects their time, their gear, and their offline life.

In one line: Teach your phone the doorbell.

Try it

See the SoundSpotter app page for the full feature list, the info table, and support links.

Use SoundSpotter, found a bug, or have a feature request? Comments are open below — anonymous is fine.