Learning and careers decision

Lingo Widget: Daily Vocabolary

A single developer can build a useful local widget-based vocabulary app (widgets, TTS, local DB, personalization heuristics) in a few weeks, but reproducing the product's claimed AI-powered personalization, curated multi-language content, and polish would require more data or server-side work, so keeping the paid product may make sense for full feature parity.

View on the App Store
You pay

Not priced

No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.

You’d pay instead

$100one-off100 h to build

$15/mo3 h/mo upkeep

No published price to break even against.

No open-source build does this yet

Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.

What a replacement has to do

  • Show a widget card with a word, example sentence and pronunciation; allow the user to mark words as learned and save words to Reminders; periodically refresh the widget with a new word tailored to user preferences.

What it still won’t have

  • Proprietary AI personalization training and server-side vocabulary generation described as "AI PERSONALIZATION"
  • Polished multi-language curated content and editorial quality across 31 languages
  • Polish around animations, video clips, and in-app journey/achievement system
  • No-account UX improvements and monetization handled by the original developer (in-app purchases flow and App Store billing analytics)

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

No published price

Lingo Widget: Daily Vocabolary does not publish a price we could read, so there is nothing to compare against. What building costs is below.

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build an iOS SwiftUI app + WidgetKit widgets and a small local database. Stack: Swift 5, SwiftUI, WidgetKit, CoreData/SQLite, AVSpeechSynthesizer (or optional cloud TTS). In scope: - Home Screen/Lock Screen widgets (Small/Medium/Large) showing a word, romanization, short definition, example sentence, and a play-pronunciation button; - local seed word import from CSV and support for loading Anki-style or CSV decks; - simple personalization: user selects native/target language, interests (travel, food, tech...), and heuristic logic to prioritize words; - track 'Learned' status and export mastered words to CSV; - save word to Reminders and schedule local review notifications; - background widget refresh scheduling (configurable intervals) and basic analytics events (local only). Out of scope: building a custom LLM, server-side vocabulary generation, multi-user sync/account system, paid in-app purchase plumbing. Include error handling for missing audio/DB and unit tests for personalization heuristics and widget data provider.
How we checked1 sources · 2/3 runs agreed · evidence score 52

How the score was reached

  • Partly verdict base52
  • Evidence score52

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 1

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded