WordCatch

An iPad and iPhone app that learns how someone with limited speech says their words, then says them clearly so everyone around them can understand.

It works alongside AAC apps like Proloquo2Go. Everything it hears and learns stays on the device.

Sam“ga-ee”“ga-ee”“ga-ee”

Dad“Cookie? You want a cookie?”

Samstops repeating

WordCatch learns“ga-ee”→cookie 🍪

Many people with limited speech repeat a word until someone says it back. WordCatch listens for that moment and learns from it, so the family teaches it just by talking the way they already do.

Speaks for them

Their word, big and out loud

Tap Playback when they say something you didn’t catch. When WordCatch recognizes a word, it shows it with its picture and says it in a natural voice. When two words sound alike, it asks instead of guessing, and the answer teaches it.

The Playback screen: one big play button and the words Tap, then let Sam talk — **Playback.** Tap once and let them talk. It stops by itself when they finish, then says what it heard.

A full-screen card showing a cookie emoji and the word cookie, with Say it again, That's right and Not right buttons — **Sure of the word.** “That’s right” turns the moment into a confirmed example.

A card asking Did Sam mean ball or bath, with a button for each — **Two words close together.** “Ball or bath?” One tap speaks the right word and teaches the difference.

Learns on its own

Listening, and finding new words

Turn on listening and WordCatch tells the communicator’s voice apart from everyone else’s, spots the repeat-until-someone-says-it moments, and saves them. When the same sound keeps getting the same answer, it suggests a new word, or adds it by itself after enough consistent answers.

The Listen screen with a Learn automatically switch, place picker, counts of learned and to-review moments, and a big microphone button — **Listen.** Learn automatically in the background, or record a moment by hand. It also learns from home videos.

The Words screen: a New words card suggesting bubbles, and a grid of word cards with emoji and progress — **Words.** “WordCatch thinks this sound means *bubbles*.” Each card shows how the person says it and how many examples there are.

Find a Symbol: a search for cookie showing cookie and biscuit pictures from OpenMoji and Mulberry Symbols — **Find a Symbol.** Pictures from free AAC symbol sets like Mulberry and OpenMoji, with the artists credited. Or use a photo, emoji, or a picture you create.

The Library's To Review tab asking Is this moon? for three recordings, with Yes and Something else buttons — **Review.** Anything it isn’t sure about waits for a quick yes or no. Every automatic decision can be undone.

The cookie word page: Sam says ga-ee, a record button, and a list of recordings — **A word.** Its recordings, how they say it, and a record button for teaching it directly.

Gets better, measurably

Progress you can show the speech therapist

WordCatch retrains itself overnight while the device charges. A new version is kept only if it scores at least as well on examples a person confirmed; otherwise it rolls back. A one-tap report summarizes every word for a speech-language pathologist or teacher.

How well it understands: first-guess accuracy, top 3 accuracy, and results for each word — **How well it understands**, word by word, tested fairly on recordings it didn’t train on.

The PDF progress report: totals, most used words, and a table of each word with how it is said, recordings, accuracy, and dates — **The progress report** (PDF and spreadsheet). Only text is shared, never recordings.

Sounds like a person

Natural voices, chosen by ear

Listen to a sample of each voice, then download only the ones you like. The AI voices run on the iPad and work offline. A family member’s own Personal Voice works too.

Voice settings: voice styles, pitch and speed sliders, and a list of natural AI voices with play and download buttons — **Voices.** Play buttons for every voice before downloading.

Welcome screen: who is WordCatch for, pronouns, age, and permissions with an Allow All button — **Setup.** Who it’s for, and every permission explained up front. Nothing personal is built into the app.

At a glance

What it does

Learns from real life. Record words, import audio and videos from Photos, or let it listen and learn when someone says a word back.

Recognizes their words from a few examples each, even words that sound alike, and gets better every night.

Tells voices apart, so it learns only from the person it’s for, and checks with you when it isn’t sure.

Playback: tap once, let them talk, and hear what they said. It stops by itself when they finish.

Speaks for them in big type and a natural voice, and asks “ball or bath?” when two words are close.

Brings in their AAC words from screenshots, word lists, board files or PDFs, with pictures from free symbol sets.

Finds new words on its own when the same sound keeps getting the same answer.

Shares progress with a speech therapist or teacher as a PDF or spreadsheet.

Works on iPad and iPhone, offline, with backups to a folder you choose.

Privacy

It stays on the device

Only their voice is kept

Other people’s speech is turned into text on the device to spot the loop, then thrown away.

Recognition runs on the device

No audio is ever sent anywhere. The optional sentence helper sends only words, never sound.

Backups you control

Scheduled backups to a folder you choose, such as iCloud Drive, with one-tap restore.