Translate PDF and Word documents between English and Malayalam

Upload an English or Malayalam Word file, or a PDF with selectable text, and get it back in the other language with its layout kept. Dates, amounts, section numbers and web addresses stay exactly as written; read the amounts, for the reason below.

English

Applications are invited under section 24(2) of the Housing Act, 2016. The last date is 31-03-2027 and the fee is Rs 250. For help write to help@example.gov.in or visit https://www.example.gov.in/apply.

Malayalam, translated

ഭവന നിയമത്തിലെ 24(2) വകുപ്പ് 2016 പ്രകാരം അപേക്ഷകൾ ക്ഷണിച്ചു. അവസാന തീയതി 31-03-2027 ഉം ഫീസ് 250 ഉം ആണ്. സഹായത്തിന് help@example.gov.in എന്ന വിലാസത്തിൽ എഴുതുക അല്ലെങ്കിൽ https://www.example.gov.in/apply സന്ദർശിക്കുക.

The three-sentence test notice, as the English-to-Malayalam translation returned it. All six protected items came back, but the word for rupees before the fee was dropped: ഫീസ് 250.

Translate a Word file, a PDF with a text layer, or a photo of a page between English and Malayalam, either way. Machine translation, in beta; a free account with a confirmed e-mail address is needed.

English to Malayalam, and Malayalam to English

Both directions work the same way. A Word file is edited where it stands: every paragraph style, table, list, header, footer and page setting stays the file’s own and only the words change, so a Malayalam circular comes back as an English circular, and an English notice as a Malayalam one, with its centred heading, numbered list and bordered table where they were. A PDF with selectable text is first turned into a Word file and then translated, so the result is a Word file you can edit, and how closely it follows the PDF is the PDF-to-Word conversion’s doing.

Translated Malayalam is set in Noto Sans Malayalam, as real Unicode text you can search and edit; if that font is not on your computer, choose any Malayalam font in Word. Numbers, dates, section references, amounts, times of day, e-mail addresses and web addresses are taken out before a sentence is sent and put back afterwards, and an answer in which one does not come back exactly once is not accepted. A sentence that still cannot be translated stays in the source language and is highlighted yellow; it is never dropped, and never filled in with a guess.

What to read carefully in the Malayalam

In the test notice the fee came back as ഫീസ് 250: the figure was kept, as every figure is, but the word for rupees in front of it was not. The figure is protected; the currency word around it is ordinary text, and the machine left it out. Translated back into English it read “the fee is 250”. In a Malayalam translation, check that every amount still says what currency it is in.

The first sentence also ran the section and the year together, 24(2) വകുപ്പ് 2016 പ്രകാരം, where the English had the year beside the Act’s name. Both numbers are right; their places are worth a look.

What was measured for Malayalam

Before Malayalam was switched on, the production pipeline translated the test notice from English into Malayalam and back. In both directions 6 of 6 protected items came back exactly: the section reference, the year, the date, the amount, the e-mail address and the web address. The Malayalam side was written in the Malayalam script, and the English read back close to the original. A Word notice with a heading, a centred line with a bold date, a numbered list, a table, a tab, a header and a footer was also translated into Malayalam and back, and its paragraph settings, table grid, page setup, header and footer were identical to the source, on the same number of pages.

That is a check of the machinery, not of the language. It says the tool kept your numbers and your layout; it does not say every sentence reads the way a Malayalam writer would put it.

Malayalam in a scan or an old font

A scanned PDF has no text to translate, so it is refused rather than guessed at. Read it first with Malayalam OCR, correct what needs correcting, and translate the Word file that comes out. Malayalam set in an old font such as ML-TT Karthika, Revathi or Akhila pastes as Latin letters; convert it to Unicode with the legacy converter first, then translate.

Footnotes, endnotes and comments are not translated yet, and the result says so. Text inside a picture is not translated. Malayalam OCR reads scans of printed Malayalam, and its Word file can be translated straight away.

What happens to each part of the file

Numbers, dates, sections, amounts, addresses
Kept exactly as written, in both directions. A sentence where one comes back changed is not accepted.
Headings, lists, tables, header and footer
Kept: the Word file is edited in place. Header and footer text is translated too.
A sentence that could not be translated
Stays in the source language, highlighted yellow, and is counted in the report.
An amount
Check its currency word: in the test, the word for rupees was dropped.
Footnotes, endnotes, comments, text in pictures
Not translated yet. The report says so.
A Malayalam reader’s check
Not done yet. Read the result before you rely on it.

Frequently asked questions

Can I translate a Malayalam document into English?

Yes: a Malayalam Word file or a PDF with selectable text in Unicode is translated into English with its layout kept. Check amounts and the place of each year, as described above.

Will the Malayalam use the old or the new script?

The translation is ordinary Unicode Malayalam, which your fonts draw in whatever style they use; the tool does not choose between the reformed and the traditional script.

Has a person who reads Malayalam checked these translations?

Not yet. No Malayalam reader has checked a translation from this tool so far; only Telugu and Hindi have been read by a person. What has been checked for Malayalam is checked by machine: that every protected item comes back, that the text is in the Malayalam script, that the layout does not change and that it reads back into English. A machine check cannot tell a good sentence from an awkward one, so read the result, and have anything official or legal checked by someone who reads Malayalam.

Is it free, and do I need an account?

A free account with a confirmed e-mail address translates its first few pages without charge, once per account; a page of translation is 2,000 characters of text, so a dense A4 page can count as more than one. Pages past the free allowance are paid in credits (one credit is one rupee) at the rate on the Pricing page, and the price is shown before anything is charged. The Limits page has the free numbers as they stand today.

What happens to my file?

It is stored encrypted while it is translated and removed by a cleanup that runs every 15 minutes, so nothing is kept longer than 4 hours after upload. The text is sent to an outside machine-translation service to be translated; the Privacy page says what is sent and what is not.

Related tools

More about translation