Epstein Extracted: search the files

Welcome to the first fully searchable version of the recently released Jeffery Epstein case files. The original files were released as 35,000+ separate images (each a photo of a single page) spread over 12 folders. In that format they are impossible to search and would require years to transcribe manually. We have extracted the digital text from all of those images and consolidated them into a single searchable database.

Original release is 35,000+ files. Each one is an image of a single page. The files are not searchable.

Using AI techniques we extracted digitized text from the images via optical character recognition (OCR).

All 35,000+ pages are placed in a single searchable database.

We hope researchers, journalists and truth seekers will find the data useful and bring full transparency to the Epstein Files. But also that historians may be interested in applying our techniques to other historical documents. Explore the rest of the site to learn more about our process or search the Epstein Files. If you find this site useful, learn how you can cite and support our work.

Page updated

Google Sites

Report abuse