Docs2{JSON}
The Docs2JSON API is the fastest, most accurate document parser and image-to-JSON solution available. Built on Google Gemini AI, it instantly converts messy, unstructured files—from PDF to JSON, Word (DOCX), and scanned images via Smart OCR—into clean, structured data. Ideal for powering AI and automation workflows. Get 90%+ accuracy without writing complex templates.
6 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Docs2{JSON} endpoints
| Method | Endpoint | Description |
|---|---|---|
| GET |
API Documentation /api/help |
Provides a Smaller version of docs on how to use this API. |
| POST |
Parse Images /api/parse/image |
Supported File Types: png, jpg, jpeg Functionality: Leverages computer vision and OCR to analyze image content and returns the same NLP-derived insights as the General Document… |
| POST |
Parse CSV File /api/parse/csv |
Supported File Types: csv Functionality: Transforms an entire CSV file into a JSON array, with keys dynamically inferred from the header row, making tabular data instantly… |
| POST |
General Document Parser /api/parse/document |
Supported File Types: pdf, txt, doc, docx Functionality: Applies Natural Language Processing (NLP) to extract deep insights, including title, summary, keywords, named entities… |
| POST |
Parse Invoice Document /api/parse/invoice |
Supported File Types: pdf, png, jpeg, jpg Functionality: Extracts core billing and transaction data—invoice number, dates, itemized lists (line items), and total… |
| POST |
Parse Resume Document /api/parse/resume |
Supported File Types: pdf, doc, docx Functionality: Extracts critical candidate information, including name, contact details, skills, work experience history, and educational… |
