Learning and careers decision
Frenchico
A solo developer can implement the core speaking-practice and AI feedback workflow using open-source components, but recreating the polished mobile apps, curated lesson library, user base, and production hardening of the commercial product is not realistic as a small one-person project.
Visit website↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off120 h to build
$100/mo6 h/mo upkeep
No published price to break even against.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Frenchico alternatives, with the arithmetic →
What a replacement has to do
- User records spoken response → audio is transcribed and analyzed by AI → feedback and score returned → progress saved and next lesson unlocked
What it still won’t have
- Polished native mobile apps and App Store / Play Store presence
- Curated, exam-aligned lesson library and editorial content
- Existing student base, reviews and brand trust
- Production-grade moderation, fraud detection, and scale-tested infra
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Frenchico 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
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
Build a minimal web-first French exam speaking-practice service using Next.js (React) + Node/Express + Postgres. Core features in scope: user auth (email), lesson CRUD and structured prompts, client-side audio capture and chunked upload, server endpoints to accept audio and call a hosted ASR (e.g., Whisper/OpenAI) and an LLM for feedback, a scoring mapper that converts LLM output to TEF/TCF-like scores, progress dashboard showing past attempts, and a 3-day free-trial gating. Out of scope: native iOS/Android builds, payment provider integration, multi-tenant enterprise features. Include input validation, retries for ASR/LLM calls, basic rate-limiting, logging, end-to-end tests for core endpoints, and instructions to deploy to a single-node VPS (Docker + docker-compose).
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 3 cited sources+3
- 3/3 assessment runs agreed+4
- Evidence score64
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 · 3
Every page the run actually retrieved.
- official productFrenchico | TEF Canada & TCF Preparation App
- open sourcemengxi-ream/read-frog
- open sourceumlx5h/LLPlayer
Integrity checks
What held up, and what did not.
