Free online tool — no sign-up
Upload a Vietnamese EPUB and get the first fifteen pages back in Japanese. Vietnamese states in every pronoun what Japanese states in every verb ending, so the two systems can actually talk to each other.
The first 15 pages of text are sent to our server to be translated. The file itself stays on your device.
When a Vietnamese character calls someone anh rather than em, they have declared the age relationship in that sentence. Japanese needs exactly that information to choose a verb ending, and normally has to guess at it when translating from a language that does not supply it. Here it is supplied, explicitly, on every line.
That does not make the job automatic. The Vietnamese pronoun tells you the relationship; which Japanese register it maps to still depends on the setting, and it has to be one mapping for the whole book rather than a fresh decision per scene.
So the model reads the entire text first and writes a guide — the cast, their relationships, the names and the recurring terms — and every page of the sample is translated against it.
A DRM-free EPUB. The file stays on your device; only the text of the sample is sent.
The cast and the pronoun relationships are mapped once, then converted into one consistent set of Japanese registers.
About 4,500 words as a complete EPUB. Japanese script renders in every modern reader.
Names are transliterated, not translated. A Vietnamese name goes into katakana, and the tone marks it carried do not survive — which is a real loss and an unavoidable one.
Horizontal, not vertical. The sample is set the way the source book was, which for a Vietnamese original means horizontally.
Register is a mapping, not an equivalence. Vietnamese and Japanese both encode relationships; they do not carve them up the same way.
Fifteen pages, not the book, and the text is sent to a server and discarded when the job ends.
By way of the relationship they declare. anh/chị/em say who is older and how close two people are, which is the information a Japanese verb ending needs — so the mapping is real rather than invented, and it is fixed once from the whole book.
They are written in katakana, which Japanese readers can pronounce. The Vietnamese tone marks have no katakana equivalent and are lost; the same name is spelled the same way throughout the sample, which is the part that can be guaranteed.
Yes, for formal and abstract vocabulary, where both languages draw on the same Chinese roots. Everyday words diverge completely, so the advantage shows up in essays and non-fiction more than in dialogue.
About 4,500 words, roughly fifteen pages, five books a day.
All free AI book tools · Free converters that run in your browser
The app runs the same engine across the entire book and can show the Japanese next to the Vietnamese, with your position synced between devices.
Open DualBook