Translate scanned document
Translate extracted PDF text into Markdown.
Translate scanned document
Drop your files here
or choose files from your device
Como usar Translate scanned document
Translate scanned document extracts the text layer from a PDF and translates it between English and Spanish with Marian models that run in your browser after a first download. It processes 1 to 30 pages, 10 by default, and up to 30,000 characters per run. The translation downloads as Markdown with a Page label for each page.
- Choose a source file. If the tool accepts multiple files, arrange them in the order you want.
- Set source language code, target language code, maximum pages.
- Run translate scanned document, review the output, then use the available copy or download controls.
Que admite esta ferramenta
English ↔ Spanish translation uses browser Marian models, downloaded on first run. Document translation exports extracted text in Markdown and does not rebuild page layout.
- Source language code
- Set this value for your task.
- Target language code
- Set this value for your task.
- Maximum pages
- Range: 1 to 30
Límites e procesamento
Image inputs: up to 32 megapixels, batches up to 10 images. Audio/video uploads: 50 MB; transcription: 120 seconds. Edited videos: 20 seconds, 4 fps and 640 pixels wide. Translation: English/Spanish, 30,000 characters; subtitles: 200 cues. Neural speech: 1,000 English characters. Model downloads and memory requirements vary by device.
Fonte de exemplo
A useful tool makes everyday work easier. Review the results before sharing.
Preguntas frecuentes
Which languages can the document translator handle?
Only English to Spanish and Spanish to English. Set the source and target codes to en and es in either order; any other combination is rejected with an error.
Will the translated document keep its original layout?
No. The tool extracts the text, translates it and exports Markdown labeled by page. Images, columns, fonts and page design are not rebuilt, so the result is a text draft to review.
Can I translate a scanned PDF that has no text layer?
Not directly. The tool reads existing PDF text and reports when no text layer is found. Run PDF OCR first to make the scan searchable, then translate the resulting file.
Where is my input processed?
Source files and text stay in this browser. The first run downloads public models from Hugging Face and local runtime assets from the site. Models may remain in the browser cache. No source upload to Vercel, Supabase or a conversion service is required.
What are the input limits?
Image inputs: up to 32 megapixels, batches up to 10 images. Audio/video uploads: 50 MB; transcription: 120 seconds. Edited videos: 20 seconds, 4 fps and 640 pixels wide. Translation: English/Spanish, 30,000 characters; subtitles: 200 cues. Neural speech: 1,000 English characters. Model downloads and memory requirements vary by device.