Writing and content decision
Novel Translator
A technical user can realistically build a usable EPUB/TXT translator (upload→LLM→export) using existing open-source tools and LLM APIs, but reproducing the full product (image OCR, polished reader, credit UX, community and proprietary tuning) is larger and operationally heavier.
Visit website↗$10/mo
$120/yr
Read off the official pricing page.
$100one-off90 h to build
$100/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 11 seats.
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 Novel Translator alternatives, with the arithmetic →
What a replacement has to do
- Upload EPUB/TXT → parse & clean file → split into translatable chunks with context + glossary → call LLM translation API → reassemble preserving formatting → present editable draft / EPUB export
What it still won’t have
- Polished, production-grade UI and reader experience
- Credit-pack billing flow and granular token-based pricing calculator
- Image OCR and image-based translation (beta) with client-side iOS app
- Community/Discord support and product documentation
- Any proprietary model optimizations or glossaries tuned by the vendor
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 11 seats.
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 Novel Translator replacement as a web app using Node.js (Express) + React frontend + PostgreSQL for glossaries/jobs + AWS S3 for file storage. Core features in scope: EPUB/TXT upload and validation, text cleaning and paragraph splitting, glossary CRUD and term-consistent post-processing, chunking logic that calls a configurable LLM API (OpenAI-compatible) with rate-limit/retry and per-file progress, reassembly preserving chapters/italics and EPUB export, and a simple account page showing remaining credits (one-off credit packs accepted via Stripe checkout). Out of scope: mobile client-side OCR app, scanned-image OCR pipeline, advanced image/bubble translation, and multi-language marketplace. Include server-side error handling, retries, input validation, unit tests for parsing/chunking/reassembly, and basic integration tests for the LLM integration.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 4 cited sources+3
- Price verified on pricing page+3
- Evidence score63
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 · 4
Every page the run actually retrieved.
- official productNovel Translator — product
- official pricingNovel Translator — pricing
- open sourcehydropix/TranslateBooksWithLLMs
- open sourcexunbu/docutranslate
Integrity checks
What held up, and what did not.
