Extract and translate text from images and PDFs using AI vision models. Supports screenshots, documents, handwriting, and scanned files.
Use your own API key to get started.
Extract text from images and PDFs using AI vision. Optional translation to 12 languages.
Configure a vision-capable API key using the banner above to enable text extraction.
PNG, JPEG, and WebP images, plus PDF documents. You can queue up to 10 files at once with each file limited to 10 MB, and PDFs are capped at 25 pages. Printed and handwritten text are both supported.
After selecting a file, check "Translate extracted text" and pick one of 12 languages: English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Russian, or Hindi. The vision model extracts the text and returns the translation in the same pass.
Each page is rendered to an image in your browser and sent to the vision model separately, in page order. The extracted results are stitched together, and any page that fails is flagged so you know which section to retry.
Yes. This is a bring-your-own-key tool: add a key for any vision-capable provider such as Gemini, OpenAI, Anthropic, Z.AI, or Kimi using the banner at the top, then choose the provider and model from the dropdowns. Your key is kept in your browser session only and is never stored on our servers.
Files stay in your browser until you press Extract Text, at which point each page or image is sent directly to the AI provider you selected using your own key. Nothing is archived on this site, and the text download is generated locally.