Is the cuneiform document translator free?

You can try it free, with no account needed, and signing in gives you a larger daily allowance. Pro and Scholar are there for longer documents and regular use.

Can it read a photo of a clay tablet?

Only partly, and you should not rely on it. Wedges are three-dimensional, so the same sign looks different under different light; tablets are curved, chipped and written small; and a photo shows one face when the text continues on the reverse and the edges. Large monumental signs, brick stamps and cones with a ruler’s standard inscription are the cases that can work, mostly because the text is formulaic and known. For a tablet you care about, look for its publication (CDLI catalogues hundreds of thousands of tablets, many with images and transliterations) and upload the hand copy or transliteration; those are read far more reliably than the clay.

Is cuneiform a language? Which language will the translation come from?

Cuneiform is a script, used for Sumerian, Akkadian (Babylonian and Assyrian), Hittite, Elamite, Hurrian, Urartian and others, much as the Latin alphabet serves English, Latin and Turkish. The translator works out the language from the text where it can, but sign values differ between languages and a mistaken guess produces a confident, wrong reading. If you know the language, say so in a note in the file or use the Sumerian or Akkadian document page directly; if the text is Hittite, the Hittite text translator handles typed transliteration.

How accurate is it? What is the difference between Fast and Advanced?

Fast gives a rough sense of what a clean transliteration says. Advanced runs a frontier model and is the tier to use for cuneiform of any kind, where a sign’s several values, Sumerograms that must be read as words of the surrounding language, silent determinatives, numbers, measures and date formulae all have to be handled at once. Neither tier makes a bad photograph readable. Treat the result as a working aid and not as a substitute for a critical edition or a published scholarly translation, and check any line you will cite against one.

Will the translation keep my document’s original layout?

The translator produces a translated PDF, Word, PowerPoint, Excel or EPUB file that aims to preserve the original layout, including tables, columns and headers. Text size, fonts and line breaks may change, so review the result against the original. Editions that set a hand copy beside a transliteration, or transliteration beside translation in parallel columns, are where the layout is most likely to shift.

Can it write my name or an English document in cuneiform?

Not on this page, which reads cuneiform into English. For a name, a motto or a short phrase, the cuneiform text translator renders English into Sumerian and writes it in Unicode cuneiform signs with a transliteration underneath, which is what most people want for a tattoo, a gift or a classroom demonstration. Rendering a whole document into cuneiform is not something to expect here.

What file types and transliteration conventions can I upload?

PDF, DOCX (Word), PPTX (PowerPoint), XLSX (Excel) and EPUB, plus photographed or scanned pages as JPG, PNG or HEIC. Transliteration with Unicode diacritics (š, ṣ, ṭ, ḫ, ĝ) and subscript numbers, the accented style (dù, sá), the ASCII style of CDLI’s ATF files (sz, s,, t,, j) and typed Unicode cuneiform are all readable. Free and Pro accept up to 20MB and 100,000 extracted characters per file; Scholar accepts up to 50MB and 1,000,000 characters.

Cuneiform PDF & Document Translator — Cuneiform to English

Read cuneiform texts in English while preserving your document’s layout. Upload a hand copy, a transliteration, a textbook page or a tablet photo, keep English as the target, and get a translation that follows the sense of the original.

Loading credits…

Translate into

Drag and drop a file here, or click to browse

PDF
DOCX
PPTX
XLSX
EPUB
JPG
PNG
TXT

See “Keep formatting” in action

Real examples of the “Keep formatting” option: original on the left, translated document on the right. Click either page to enlarge.

1 / 6

A civil complaint filed in Mexico City, Spanish to English. Caption block, numbered pleadings, the evidence table and the signature block all keep their places. — Original — A civil complaint filed in Mexico City, Spanish to English. Caption block, numbered pleadings, the evidence table and the signature block all keep their places.

An Italian birth certificate, photographed rather than scanned. The framed masthead, the field grid, the marginal annotations and the round seal all hold their positions. — Original — An Italian birth certificate, photographed rather than scanned. The framed masthead, the field grid, the marginal annotations and the round seal all hold their positions.

A handwritten archaeological field notebook from 1974. The engine reads the hand and keeps the ruled inventory table intact. — Original — A handwritten archaeological field notebook from 1974. The engine reads the hand and keeps the ruled inventory table intact.

A handwritten archaeological field notebook from 1974. The engine reads the hand and keeps the ruled inventory table intact. — Translation — A handwritten archaeological field notebook from 1974. The engine reads the hand and keeps the ruled inventory table intact.

A German hospital discharge summary. Diagnoses with ICD codes, lab values and the medication table survive the translation unchanged. — Original — A German hospital discharge summary. Diagnoses with ICD codes, lab values and the medication table survive the translation unchanged.

A German hospital discharge summary. Diagnoses with ICD codes, lab values and the medication table survive the translation unchanged. — Translation — A German hospital discharge summary. Diagnoses with ICD codes, lab values and the medication table survive the translation unchanged.

A 1747 parish baptism register in Latin. Ruled columns, godparents and marginal notes stay aligned, so the genealogy still reads as a register. — Original — A 1747 parish baptism register in Latin. Ruled columns, godparents and marginal notes stay aligned, so the genealogy still reads as a register.

A 1747 parish baptism register in Latin. Ruled columns, godparents and marginal notes stay aligned, so the genealogy still reads as a register. — Translation — A 1747 parish baptism register in Latin. Ruled columns, godparents and marginal notes stay aligned, so the genealogy still reads as a register.

A scanned 17th-century Italian index of sermons. Two columns of dense small print, translated in place. — Original — A scanned 17th-century Italian index of sermons. Two columns of dense small print, translated in place.

A scanned 17th-century Italian index of sermons. Two columns of dense small print, translated in place. — Translation — A scanned 17th-century Italian index of sermons. Two columns of dense small print, translated in place.

How Cuneiform documents come out

Upload a hand copy, a transliteration, a sign list, a textbook page or a photograph of a tablet and read the text in English. Cuneiform is a writing system rather than a language: the same wedges wrote Sumerian, Akkadian, Hittite, Elamite, Hurrian and more, so knowing which language your text is in matters as much as reading the signs. Photographs of clay tablets are the weakest input, because a wedge is a shadow that changes with the light; published hand copies, typed Unicode cuneiform and transliterations come through far better.

Cuneiform was pressed into damp clay with a reed stylus, so a sign is a pattern of wedges with depth rather than a line on a flat surface, and a tablet continues from its obverse onto its reverse by flipping bottom over top, with text often running around the edges. The earliest tablets were written in columns of cases; on most tablets from the late third millennium onward the lines run left to right, while monuments such as the Hammurabi stele kept the older vertical arrangement. Most signs are polyvalent: one sign can stand for several syllables and for a whole word, and which value applies depends on the language and the period. Sign shapes changed enormously between the archaic pictographs of Uruk, the cursive hands of Old Babylonian scribes and the standardized forms of the Neo-Assyrian libraries, which is why a sign list such as Labat’s Manuel d’épigraphie akkadienne shows each sign period by period, and Borger’s Mesopotamisches Zeichenlexikon catalogues its readings. Unicode has had a cuneiform block since 2006, but a font gives each sign one period’s shape, so a Unicode rendering of an Ur III text may look nothing like the tablet it came from. A document built from this material stacks photographs, the line drawings (hand copies) that editors publish, and transliteration with hyphens between signs, subscript index numbers, superscript determinatives, capitals for logograms and brackets for what is broken. Clean transliteration is the layer that reads most reliably.

Translate your document and keep its structure

The translator keeps your file’s structure while translating the text in context. The downloaded format depends on the source file.

PDFs and scanned pages: The translated PDF follows the page visually, with translated pages rendered as images. Selectable PDF text and identical fonts are not guaranteed.
Word documents and PowerPoint presentations: Start with DOCX or PPTX when you have it. Native paragraphs, table text and slide text can stay editable in the corresponding file format. Translated text inside pictures remains image content; review text wrapping and font changes in your editor.
Excel workbooks and EPUB books: Use the original XLSX or unprotected EPUB for a translated workbook or ebook. Review formulas, numbers and text cells in a workbook; check chapter order, navigation and text flow in your ebook reader.

What people translate to and from Cuneiform

Tablet photographs and museum objects

Photographs of tablets in a museum case, a brick or cone bought at auction, or a tablet in a dig report come with an honest warning: sign reading from a picture is not reliable. A wedge is a shadow that moves with the light, administrative tablets are written small and dense, surfaces are chipped and salted, and a photo usually catches one face at an angle. What can work is identification: recognising a Nebuchadnezzar brick stamp, an Ur III receipt, a Gudea cone or a school exercise from its shape and layout, and reading the large, clear signs of monumental inscriptions. For anything more, find the object’s publication, which for many tablets is online with a hand copy and a transliteration, and upload that.

Hand copies, sign lists and published editions

Assyriologists publish tablets as hand copies, line drawings that flatten the wedges into ink, and those read better than photographs, especially at the scale of a printed plate. Series volumes with a copy and a transliteration on facing pages, sign lists giving period forms and reading values, and lexical lists are common uploads. Expect the translation to lean on the transliteration wherever the page has one and on the drawing where it does not. A copy of a damaged tablet carries the copyist’s hatching and dotted outlines for broken signs, and those should come through as gaps in the English rather than as invented words; check that they do.

Transliterations and course materials

The strongest input is a transliteration: an export from CDLI or ORACC, an ETCSL text, a passage from Huehnergard’s A Grammar of Akkadian or Foxvog’s Introduction to Sumerian Grammar, or a handout of sign values and vocabulary. The conventions are read as conventions: hyphens join the signs of one word, subscript or accented index numbers (du₃, dù) tell homophonous signs apart, superscript d and ki are determinatives, capitals mark logograms or uncertain readings, and square and half brackets mark damage. If you know which language the text is in, the dedicated pages give a closer reading and describe the texts people actually bring.

Working out which language a text is in

The same signs wrote Sumerian, a language isolate, across three thousand years of administrative and literary texts; Akkadian, in its Babylonian and Assyrian dialects, for laws, letters, epics and royal annals; Hittite in Anatolia; and Elamite, Hurrian and Urartian on the edges of the cuneiform world. Old Persian cuneiform is a separate and far simpler script of a few dozen signs, and Ugaritic is an alphabet written with wedges. Some clues: Sumerian transliteration is long chains of short syllables with case endings at the end of a phrase, Akkadian mixes capitalised Sumerograms with syllabic spellings, and a museum label or edition usually says. Name the language in the file or a note if you know it.

What to watch for in Cuneiform document translation

The traps in cuneiform are mostly about reading before translating. Almost every sign has several values: KA alone can be read ka, zú, du₁₁ or inim, and a wrong choice gives a different word. Determinatives are not pronounced (the superscript d before a god, ki after a place, ĝiš before wooden things), so they must vanish in English rather than surface as syllables. A Sumerogram inside an Akkadian text is read as the Akkadian word (LUGAL is šarru), while the same sign in a Sumerian text is the Sumerian word. Numbers are sexagesimal, the same vertical wedge can write 1 or 60 depending on its position, and quantities come with capacity and weight measures (gur, sìla, mina, shekel) that must stay as measures. Dates are year names in Ur III and Old Babylonian texts and eponym officials in Assyria, so a date line is a small historical statement, not a number. ASCII transliterations follow their own spelling (sz for š, s, for ṣ, t, for ṭ, j for ĝ in the ATF format used by CDLI), which looks like typos to a reader that does not know it. And a Unicode font’s glyphs are one period’s shapes, so a sign typed in Unicode may look unlike anything on an Old Babylonian tablet; where the text matters, work from the transliteration and keep the editor’s brackets in view.

Cuneiform document translation FAQ

Is the cuneiform document translator free?: You can try it free, with no account needed, and signing in gives you a larger daily allowance. Pro and Scholar are there for longer documents and regular use.
Can it read a photo of a clay tablet?: Only partly, and you should not rely on it. Wedges are three-dimensional, so the same sign looks different under different light; tablets are curved, chipped and written small; and a photo shows one face when the text continues on the reverse and the edges. Large monumental signs, brick stamps and cones with a ruler’s standard inscription are the cases that can work, mostly because the text is formulaic and known. For a tablet you care about, look for its publication (CDLI catalogues hundreds of thousands of tablets, many with images and transliterations) and upload the hand copy or transliteration; those are read far more reliably than the clay.
Is cuneiform a language? Which language will the translation come from?: Cuneiform is a script, used for Sumerian, Akkadian (Babylonian and Assyrian), Hittite, Elamite, Hurrian, Urartian and others, much as the Latin alphabet serves English, Latin and Turkish. The translator works out the language from the text where it can, but sign values differ between languages and a mistaken guess produces a confident, wrong reading. If you know the language, say so in a note in the file or use the Sumerian or Akkadian document page directly; if the text is Hittite, the Hittite text translator handles typed transliteration.
How accurate is it? What is the difference between Fast and Advanced?: Fast gives a rough sense of what a clean transliteration says. Advanced runs a frontier model and is the tier to use for cuneiform of any kind, where a sign’s several values, Sumerograms that must be read as words of the surrounding language, silent determinatives, numbers, measures and date formulae all have to be handled at once. Neither tier makes a bad photograph readable. Treat the result as a working aid and not as a substitute for a critical edition or a published scholarly translation, and check any line you will cite against one.
Will the translation keep my document’s original layout?: The translator produces a translated PDF, Word, PowerPoint, Excel or EPUB file that aims to preserve the original layout, including tables, columns and headers. Text size, fonts and line breaks may change, so review the result against the original. Editions that set a hand copy beside a transliteration, or transliteration beside translation in parallel columns, are where the layout is most likely to shift.
Can it write my name or an English document in cuneiform?: Not on this page, which reads cuneiform into English. For a name, a motto or a short phrase, the cuneiform text translator renders English into Sumerian and writes it in Unicode cuneiform signs with a transliteration underneath, which is what most people want for a tattoo, a gift or a classroom demonstration. Rendering a whole document into cuneiform is not something to expect here.
What file types and transliteration conventions can I upload?: PDF, DOCX (Word), PPTX (PowerPoint), XLSX (Excel) and EPUB, plus photographed or scanned pages as JPG, PNG or HEIC. Transliteration with Unicode diacritics (š, ṣ, ṭ, ḫ, ĝ) and subscript numbers, the accented style (dù, sá), the ASCII style of CDLI’s ATF files (sz, s,, t,, j) and typed Unicode cuneiform are all readable. Free and Pro accept up to 20MB and 100,000 extracted characters per file; Scholar accepts up to 50MB and 1,000,000 characters.

See “Keep formatting” in action

Real examples of the “Keep formatting” option: original on the left, translated document on the right. Click either page to enlarge.

1 / 6

Translate documents in other languages

Cursive documents German documents Egyptian Hieroglyphs documents Greek documents Elvish documents Middle English documents French documents Old French documents Ancient Greek documents Gujarati documents Cuneiform text translator All document translation