The archive · Education & Work · Product decision · 2022–2024
Glossarie bets embedded translations in eBooks can teach languages; 363 HN points
Language app that swaps English words in eBooks for French, Italian or Spanish while you read; Show HN on 2024-03-24 drew 363 points and 155 comments.
Glossarie
What the business is
Glossarie is a language-learning app that takes an English eBook and progressively swaps words and short phrases into French, Italian or Spanish at a chosen difficulty, with tap-to-see translations, grammar explanations and practice built around the text.
How it started
Founder jonathanb88 spent over two years building Glossarie with his partner, a language teacher, before the March 2024 Show HN. His premise: vocabulary is easier to remember in context and with regular repetition, and reading needs no carved-out time — other apps demand a habit of exercises or games, whereas lots of people already read books. The free app targeted French, Italian and Spanish from English.
What happened
The launch thread mixed enthusiasm with sharp pushback. Commenters praised the concept and filed feature requests, while critics asked how word-by-word replacement avoids teaching wrong word order — one screenshot rendered French 'mort' after the noun in English order — noted similar ideas in Readlang, Toucan and LingQ, and hit platform gaps: iOS 17+ only, Play Store links failing outside supported regions, and no visible pricing. The founder answered that the real tradeoff is optimizing repetition of vocabulary against quality of grammar examples, called the app 'very much at a proof of concept stage', and positioned it as a free MVP to gather feedback.
No ending yet — it is still running.
Background
Glossarie is a language-learning app that embeds the target language into reading rather than drills: it takes an English eBook and swaps a growing share of words and short phrases into French, Italian or Spanish as the reader progresses, with translations, grammar explanations and practice tied to the text. The idea is that vocabulary sticks when met in context and repeated naturally, and that reading needs no separate study habit.
The bet, in the founder's own framing, is that the approach works if there are scalable ways to improve accuracy and choose the right phrases — language analysis, NLP and LLMs — and fails if accuracy improvements quickly hit diminishing returns and demand an explosion of rules or human proofing. Jonathan (HN: jonathanb88) built the app over two years with his partner, a language teacher, and said LLMs were a step change: translations are precomputed at moderate cost with no ongoing API calls per user, while models explain translations and check accuracy.
The Show HN on 2024-03-24 drew 363 points and 155 comments. Reception was genuinely mixed: many commenters tried the app that day and praised the concept and design, while the technical discussion probed word-order errors in generated phrases, the difference from LingQ/Readlang/Toucan-style tools, iOS 17 minimums, region restrictions tied to Project Gutenberg books, and the absence of a pricing page or business model.
By the end of the thread the founder had promised fixes for the top UX complaints and confirmed the free MVP had no plans to charge for current features; dynamic difficulty, full-sentence translation and more practice features stayed on the roadmap. The source material records nothing after the thread, so no later company state is claimed.
What has to be true
- Concrete traction: 363 points and 155 comments on the 2024-03-24 Show HN, with commenters testing the app during the thread.
- The founder named a falsifiable bet: in-context translation works only if scalable NLP/LLM accuracy gains beat diminishing returns and rule explosions.
- The design attacks habit friction — users read books they already wanted to read instead of adding a daily app ritual — a different wedge from flashcard and exercise apps.
- Cost structure is unusual: content is precomputed once, so LLMs add capability (explanations, accuracy checks) without per-user API costs at reading time.
What can be applied
Build on habits users already have (reading) instead of demanding a new one, and state the scaling assumption — here, accuracy must improve via scalable NLP, not rules — so the bet stays testable.
Aftermath
As of 2024-03-25, when the Show HN discussion wound down, Glossarie was a free live MVP: an app for learning French, Italian and Spanish from English eBooks, with EPUB uploads and a public-domain library, restricted to regions where the founder had cleared book copyright. The founder collected a long feature list (dynamic difficulty, content-linked practice, browser support, more languages) and promised no charges for current features. The source material records no pricing, funding, revenue or later state, so nothing beyond the thread is claimed.
Sources
spotted an error? The archive wants to know.
Your turn
You just read one. Describe what you are building, and see who is betting on the same thing.
Free account · 3 free questions · no card