Glosso Studio
An Android language course that grades your pronunciation one sound at a time, in English and Russian. Free during the open beta; scoring runs in the cloud or, optionally, on your phone.
- Role
- Side project · product, engineering and design
- Stack
- 2
- courses live on Google Play: English and Russian
- ~342 MB
- optional on-device model, works offline
- ~130
- downloads in open beta, around 30 monthly users
Most pronunciation apps push your speech through speech-to-text and tell you whether the words matched. That says almost nothing about how you sound. Glosso gives a verdict on each individual sound: which phonemes you hit, which drifted, and where inside the word the problem is.
It’s in open beta on Android, with an English course (British or American accent) and a beginner Russian course: no ads, no payment while the beta lasts.
What it does
- Records a sentence and scores each phoneme on its own.
- Names the sound that slipped: for example, /t/ where the word needed /θ/.
- Shows the IPA of what it heard, next to a reference pronunciation.
- Builds the next drill from your own errors and tracks each sound over time.
Where scoring runs
- Cloud by default. A normal install sends the recording over HTTPS to Glosso’s own server, where it is scored in memory and discarded as soon as the request ends. It is never stored, sold or used to train models.
- Optional on-device. Settings offers a one-time download of an acoustic model (about 342 MB). With it installed, scoring runs entirely on the phone and works offline. Delete it any time to go back to cloud scoring.
There is no mandatory account and no sign-up wall: progress stays on the device. No advertising or third-party tracking SDKs are in the build.
The app does send first-party usage statistics to the same server (screens opened, lessons finished, errors), linked to a random installation id, never to your name or email, and never your audio or anything you type. They’re on by default, the app says so when you start, and you can turn them off and delete them in Settings.
Limits
If the recording has no usable speech, or is too noisy or too quiet, Glosso says the attempt could not be evaluated instead of showing 0/100. The score is an estimate, not a certificate: even native speakers don’t always get the top score, and that’s one of the things I’m still improving.
Stack
One Kotlin Multiplatform engine does the phonetics, shared between the Android app and the scoring service so both paths agree. Compose for the app, ONNX Runtime with an acoustic model for inference, Ktor for the service. Android 8.0 or newer.
Where it is now
Glosso is in a stable phase. Instead of adding features, the work goes into the pronunciation engine and into new languages, one at a time. I wrote about how it got here in What I learned building an app that listens to how you pronounce.
Beta
The beta stays open until . Everything built so far is free to use, and what you report decides what gets built next. Try it, look at your pronunciation, tell me what works and what doesn’t.
Beta Founder. Join during the beta and you’re a Beta Founder for good, even if you change plan later. When the beta ends you keep the status and get special benefits, including better terms for Glosso Pro. The exact benefits aren’t decided yet; they’ll take shape during the beta.
After the beta. When the beta ends, Glosso doesn’t stop being free. From 2028 there will be three tiers: Free (the basics, free for anyone), Pro (more advanced features and analysis) and Personalised (practice adapted to each student from their own results). The details get decided during the beta, based on how it goes.
Glosso is a proprietary product. It grew out of an earlier offline phonetic prototype, but the current app is a separate codebase.
Drafted with AI, edited by hand. I publish it when it sounds like me.