PDF Translator

Commercial use OK 380+ models No watermark No sign-up needed
Model:
+ GPT-5, Claude, Gemini
Upload a PDF and translate it into any of 99 languages. Source language is auto-detected from the document. Output is a clean plain-text or .docx file with one paragraph per source paragraph. Re-flowed PDF (translated back into the original layout) is not supported yet — use .docx for editing.

Drag a PDF here or click to upload

PDF up to 50 MB. Scanned PDFs need OCR first.

· ·
Scanned PDF detected — translate works best on text PDFs. Run OCR first. Go to PDF OCR →
This PDF is password-protected. Unlock it first. Unlock PDF →
Layout-preserving PDF output not yet supported.
Token estimate
Upload a PDF to see the exact token cost.
Translated document
Download

        

Common use cases

International reports

Translate an annual report, compliance filing, or partner MOU into your working language overnight.

Research papers

Read papers in languages you do not speak — physics from Chinese arXiv, pharma trials in Japanese.

Cross-border contracts

Translate German / Spanish / Arabic contracts into English for an internal read-through before sign-off.

Textbooks

Translate a textbook chapter for students who need it in their first language.

Free.ai vs the paid translators

Free.aiDeepL ProGoogle Cloud TranslateSmallpdf
Starting priceFree$8.99/mo$20/M chars$9/mo
Languages993313425
.docx output
Public API
Works without signup
Advanced options
Result
Tokens running low. Get More Tokens
Want better results? Premium models (GPT-5, Claude, Gemini) deliver higher quality. View Plans

❤️ Love Free.ai? Tell your friends!

Sign up to get a referral link and earn 25,000 tokens per friend.

Want more? Sign up free for 5K tokens/day + 10K bonus
Sign Up Free

Processing your request...

Translate PDFs into any language with free AI. Layout and formatting preserved.

How to Use PDF Translator

1
Enter your input

Type text, upload a file, or describe what you want. No account needed.

2
Click generate

Our AI processes your request in seconds using the best open-source models.

3
Download & share

Download, copy, or share your result. Free for personal and commercial use.

Use this tool via API

Automate this tool from your own code. OpenAI-compatible REST endpoint, Bearer-token auth, no extra SDK required. Token costs match the web interface.

curl -X POST https://api.free.ai/v1/pdf/extract/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"file": "@document.pdf"}'

PDF Translator — FAQ

Upload a PDF and translate the full text into any of 99 target languages. Source language is auto-detected, output comes back as .txt or .docx with one paragraph per source paragraph. Best for documents where content matters more than layout.

About 400 tokens per page, 600-token floor. A 20-page document costs ~8,000 tokens. The exact quote appears after upload — we call /v1/pdf/translate-quote/ with the real page count before you submit.

99 target languages covering Europe (English, Spanish, French, German, Italian, Portuguese, Polish, Russian, Dutch, Swedish, Greek, Ukrainian, etc.), Asia (Chinese simplified + traditional, Japanese, Korean, Hindi, Bengali, Tamil, Thai, Vietnamese, Indonesian), Middle East (Arabic, Hebrew, Persian), and Africa (Swahili, Hausa, Yoruba, Zulu, Afrikaans, Amharic). Source auto-detect works across all of them.

MadLAD-400, a 10B-parameter self-hosted open-source translation model with 450+ language pairs. Runs on our GPU4 — no third-party API, no data leaves our infrastructure. For comparison, DeepL supports 33 languages and Google Cloud Translate charges $20/M characters.

Not yet. Layout-preserving PDF output (re-flow into the original pages) requires a layout analysis model we have not integrated. The .docx output preserves paragraph breaks and page boundaries so you can do a final layout pass in Word if needed.

MadLAD needs extracted text. If the PDF is image-only, run /pdf/ocr/ first to get a text-layer PDF or .txt, then feed the result back into the translator. We auto-detect scanned PDFs on upload and link you to the right tool.

We render one Word paragraph per source paragraph, with a page break at every original page boundary. Opens cleanly in Word, LibreOffice, Pages, Google Docs.

50 MB per upload. Very long PDFs (200+ pages) are still supported — the translator iterates per page and takes ~3 seconds per page. The heavy-task banner appears automatically above 5 pages so you can close the tab and get an email when it finishes.

Paragraph breaks and page boundaries yes. Bold/italic/tables/lists — no, the translator operates on plain text. For layout-critical documents, translate to .docx and reapply formatting in Word.

No. Uploaded PDFs are extracted, translated, and the source file deleted. The translated output is kept on our CDN for 24 hours (7 days on a paid plan) at the share link.

Yes — POST multipart to /v1/pdf/translate/ with file + source + target + output_format fields. Quote endpoint: /v1/pdf/translate-quote/?pages=N&target=LL. Full curl recipe at /api/.

Free.ai is free, supports 99 languages, ships .docx output, and exposes a public API. DeepL Pro ($8.99/mo, 33 languages), Google Cloud Translate ($20 per 1M characters), Smallpdf ($9/mo, 25 languages, no API).

Sign up free for 10,000 tokens

Create Free Account

No credit card required

How would you rate this tool?

Love Free.ai? Tell your friends!