{"id":"zerox","name":"Zerox","maker":"Omni AI","url":"https://github.com/getomni-ai/zerox","repo":"getomni-ai/zerox","package":"pypi:py-zerox","summary":"A library that converts a document to Markdown by rendering pages as images and asking a vision model to transcribe them.","details":"Versions exist for Node and Python, and the model provider is chosen by the developer. It runs locally against hosted model APIs and is MIT licensed. It fits pages where layout is hard to recover from the file structure, such as scans.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"documents","category_name":"Document parsing and extraction","page":"https://modelmoot.com/tools/zerox","reviewed":"2026-11-15","checked":{"at":"2026-11-15T17:14:07.328Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}