Tools

DOCX to JSON API

Submit any Word document. Get back text content as searchable chunks, metadata, author, title, and a thumbnail as structured JSON.

Try it below:

FILEDrop a file or click to upload

Production-ready

Private by design

Security-first

Scalable

Production-ready

Private by design

Security-first

Scalable

Production-ready

Private by design

Security-first

Scalable

Turn Word documents into structured JSON

Upload a DOCX file or submit a URL, get structured JSON back.

{
  "kind": "document",
  "name": "Sarah Chen — CV",
  "state": "completed",
  "extraction": {
    "common": {
      "mimeType": "application/pdf",
      "size": 156672,
      "thumbnail": "https://cdn.exabase.io/...",
      "chunkCount": 14
    },
    "document": {
      "pages": 2,
      "author": "Sarah Chen",
      "title": "Sarah Chen — CV",
      "creationDate": "2025-04-12T00:00:00.000Z",
      "pdfRender": { "url": "https://cdn.exabase.io/..." },
      "documentType": "resume",
      "structured": {
        "name": "Sarah Chen",
        "email": "sarah.chen@example.com",
        "phone": "+1 (415) 555-0182",
        "summary": "Full-stack engineer with 6 years of experience building data pipelines and developer tools. Previously at Stripe and Vercel.",
        "experience": [
          {
            "company": "Vercel",
            "title": "Senior Software Engineer",
            "startDate": "2022-03",
            "endDate": "2025-04",
            "description": "Led development of the edge middleware runtime. Reduced cold start latency by 40%."
          },
          {
            "company": "Stripe",
            "title": "Software Engineer",
            "startDate": "2019-06",
            "endDate": "2022-02",
            "description": "Built internal tools for payment reconciliation. Processed $2B+ in daily transaction volume."
          }
        ],
        "education": [
          {
            "institution": "UC Berkeley",
            "degree": "B.S. Computer Science",
            "graduationDate": "2019"
          }
        ],
        "skills": ["TypeScript", "Python", "PostgreSQL", "AWS", "Kubernetes", "React", "Node.js"]
      }
    }
  }
}

Start for free

Read the docs

What is Exabase's DOCX to JSON API?

Submit a DOCX file to the Exabase Extract API and get structured JSON back. The response includes the document title, author, page count, creation date, MIME type, file size, a CDN-hosted thumbnail, a rendered PDF version, and the full text content split into searchable chunks. The API handles the parsing. No python-docx, no mammoth.js, no LibreOffice on your end.

This is the same POST /v2/extract endpoint used for all content types. When the API recognises a Word document, it extracts the text, generates a rendered version, and returns structured output. For Word documents containing invoices, contracts, or resumes, the API also detects the document type and populates extraction.document.structured with type-specific fields, just as it does for PDFs.

What you get back

The response includes the document metadata (title, author, page count, creation date), a CDN-hosted thumbnail, a rendered PDF version, and the full text as searchable chunks. Each chunk has a sequence number, the extracted text, and a page number. For recognised document types, structured fields appear alongside the metadata. The API reference has the complete response schema.

One multi-modal API

The same POST /v2/extract endpoint handles every content type Exabase supports. For DOCX files, it returns text chunks with page numbers and document metadata. For PDFs, it does the same with structured field extraction for recognised types. For EPUBs, it returns book metadata and text chunks. For audio and video, it generates transcripts with timestamps. For images, it runs OCR. For web pages, it renders JavaScript and extracts the content.

The submission flow is identical across all types: one endpoint, one SDK method, one webhook configuration. You learn the pattern once and use it for everything. The Extract docs cover each content type in detail.

What you can build with it

The structured chunks are the same format used across the Exabase platform. Feed them into a RAG pipeline so your agent can reference and cite specific passages. Build a document management system where uploaded Word files are parsed and indexed automatically. Process internal reports, proposals, and memos and make them searchable across your organisation.

Store extracted documents as Resources in a Base and the content becomes searchable through Deep Search at the paragraph level. Workers can process new uploads on a schedule, keeping your knowledge base current without manual work.

Beyond extraction

The Extract API returns more than text chunks. You get a CDN-hosted thumbnail, a rendered PDF version, and standard document metadata. Store the output as a Resource and it's searchable through Deep Search immediately. Extract key details into Memory so your agent retains what it read between sessions.

Start for free

Read the docs

How do I use it?

  1. Get your API key

Free, no credit card:

Sign up at exabase.io and copy your API key from the dashboard.

  1. Submit a Word document

Using the SDK (Node.js):

import { Exabase } from "@exabase/sdk";
import { createReadStream } from "fs";

const api = new Exabase({
  apiKey: process.env.EXABASE_API_KEY,
});

const job = await api.extract.createFromFile({
  file: createReadStream("./project-proposal.docx"),
  name: "Project Proposal — Q3 2026",
});

console.log(job.id);    // extraction job id
console.log(job.state); // "pending"

  1. Get the result

Poll the job until state reaches completed, or skip polling entirely with webhooks.

const result = await api.extract.get({ jobId: job.id });

if (result.state === "completed") {
  console.log(result.extraction?.document?.title);
  console.log(result.extraction?.document?.author);
  console.log(result.extraction?.document?.pages);
  console.log(result.extraction?.common?.chunkCount);
  console.log(result.extraction?.common?.thumbnail);
}

One API call. No python-docx, no mammoth.js, no LibreOffice.

What you get back

Field

Type

Description

state

string

completed or failed

kind

string

document

[...].mimeType

string

application/vnd.openxmlformats-officedocument.wordprocessingml.document

[...].size

number

File size in bytes

[...].thumbnail

string

CDN-hosted thumbnail URL

[...].chunkCount

number

Number of text chunks

[...].pages

number

Page count

[...].author

string

Document author

[...].title

string

Document title

[...].creationDate

string

Document creation date

[...].pdfRender.url

string

CDN-hosted rendered PDF URL

Text chunks are retrieved separately via GET /v2/extract/{jobId}/chunks.

Each chunk includes a sequence number, the extracted text, and a page number.

API quick reference

Endpoint

Method

Description

/v2/extract

POST

Submit extraction job

/v2/extract

GET

List extraction jobs

/v2/extract/{jobId}

GET

Poll for result

/v2/extract/{jobId}/chunks

GET

Fetch text chunks

/v2/extract-settings

PUT

Configure webhook

Auth: X-Api-Key header on all requests.

File retention: Stored files are retained for 1 day from job creation. Download or copy anything you need before they expire.

Need file extraction or full page content?

Exabase offers a full set of tools to extract content from any media, document or website.

All your data extraction needs in one place.

Learn about Exabase Extract →

Why Exabase

No document processing library

The API handles DOCX parsing, text extraction, and rendering. No python-docx, no mammoth.js, no LibreOffice. Submit a file, get structured output.

No document processing library

The API handles DOCX parsing, text extraction, and rendering. No python-docx, no mammoth.js, no LibreOffice. Submit a file, get structured output.

Rendered PDF included

Every DOCX extraction generates a rendered PDF version hosted on the Exabase CDN. Display it in your UI or offer it as a download without running a conversion tool.

Rendered PDF included

Every DOCX extraction generates a rendered PDF version hosted on the Exabase CDN. Display it in your UI or offer it as a download without running a conversion tool.

Structured document detection

If the Word document contains an invoice, contract, or resume, the API detects the type and extracts structured fields automatically. Same capability as PDF extraction.

Structured document detection

If the Word document contains an invoice, contract, or resume, the API detects the type and extracts structured fields automatically. Same capability as PDF extraction.

Text as searchable chunks

Extracted text is split into structured chunks with page numbers. Feed them into RAG pipelines, build search indexes, or pass them as LLM context.

Text as searchable chunks

Extracted text is split into structured chunks with page numbers. Feed them into RAG pipelines, build search indexes, or pass them as LLM context.

One API for everything

The same POST /v2/extract endpoint handles DOCX, PDF, EPUB, PPTX, images, audio, video, and web pages. Learn one API, extract from anything.

One API for everything

The same POST /v2/extract endpoint handles DOCX, PDF, EPUB, PPTX, images, audio, video, and web pages. Learn one API, extract from anything.

Webhooks with delivery logs

No need to poll. Configure a webhook URL and get notified on completion. Every delivery attempt is logged with status codes and response bodies. You can manually re-trigger a webhook if your server missed it.

Webhooks with delivery logs

No need to poll. Configure a webhook URL and get notified on completion. Every delivery attempt is logged with status codes and response bodies. You can manually re-trigger a webhook if your server missed it.

Reprocess without re-uploading

If a job fails, call the reprocess endpoint. The API retries using the original file without requiring a new upload.

Reprocess without re-uploading

If a job fails, call the reprocess endpoint. The API retries using the original file without requiring a new upload.

Async processing that scales

Submit hundreds of documents and let the pipeline handle them. Poll for results or set up webhooks and process completions as they arrive. No timeouts.

Async processing that scales

Submit hundreds of documents and let the pipeline handle them. Poll for results or set up webhooks and process completions as they arrive. No timeouts.

Not just extraction

DOCX extraction is one endpoint. The same Exabase account gives you Memory, Deep Search, Resources, and Workers. Same API key, different endpoints.

Not just extraction

DOCX extraction is one endpoint. The same Exabase account gives you Memory, Deep Search, Resources, and Workers. Same API key, different endpoints.

Comparisons

vs mammoth.js / python-docx

These libraries parse DOCX files locally. You install them, write extraction code, handle edge cases (tables, headers, footnotes, embedded objects), and build the chunking logic yourself. Exabase is one API call that returns structured chunks with page numbers. The infrastructure is managed for you.

vs Pandoc

Pandoc converts between document formats. It's powerful but requires local installation, command-line orchestration, and infrastructure management. Exabase is an API. Submit a file, get JSON back. No installation, no process management.

vs Aspose

Aspose offers document processing SDKs for Word, PDF, and other formats. It's a large, enterprise-oriented SDK with per-developer licensing. Exabase is a lightweight API call. The extracted content feeds directly into the rest of the platform if you need storage, search, or automation.

Works with other Exabase features

Memory

Self-managing advanced memory system.

Bases

Isolated per-tenant instances with version rollback.

Resources

Files, notes, links. Your portable context server.

Deep Search

Sub-document multi-modal hybrid search.

Extract

Structured data from PDFs, websites, images, and more.

Workers

Autonomous agents and self-enriching knowledge bases.

Memory

Self-managing advanced memory system.

Bases

Isolated per-tenant instances with version rollback.

Resources

Files, notes, links. Your portable context server.

Deep Search

Sub-document multi-modal hybrid search.

Extract

Structured data from PDFs, websites, images, and more.

Workers

Autonomous agents and self-enriching knowledge bases.

Ready for scale

Fast

Deliver speed to your users. Infrastructure that won't slow your agent down.

Secure

Encrypted in transit (SSL) and at rest (AES-256). CASA certified.

Reliable

99.9% uptime. Built on Exabase's consumer-grade scaled infrastructure.

Ready for scale

Fast

Deliver speed to your users. Infrastructure that won't slow your agent down.

Secure

Encrypted in transit (SSL) and at rest (AES-256). CASA certified.

Reliable

99.9% uptime. Built on Exabase's consumer-grade scaled infrastructure.

Ready for scale

Fast

Deliver speed to your users. Infrastructure that won't slow your agent down.

Secure

Encrypted in transit (SSL) and at rest (AES-256). CASA certified.

Reliable

99.9% uptime. Built on Exabase's consumer-grade scaled infrastructure.

Use cases

RAG pipelines

Extract text chunks from Word documents and feed them into your retrieval-augmented generation pipeline. Each chunk includes a page number for source attribution.

Document management systems

Auto-extract metadata and generate thumbnails for every Word document uploaded to your platform. Display page count, author, and a visual preview without opening the file.

Document management systems

Auto-extract metadata and generate thumbnails for every Word document uploaded to your platform. Display page count, author, and a visual preview without opening the file.

Knowledge base ingestion

Bulk-process a library of Word documents and store them as searchable Resources. Your agent gets precise context from the documents it has indexed.

Knowledge base ingestion

Bulk-process a library of Word documents and store them as searchable Resources. Your agent gets precise context from the documents it has indexed.

Internal document search

Index reports, proposals, memos, and policies. Search across all documents by keyword, topic, or author. Deep Search returns results at the paragraph level.

Internal document search

Index reports, proposals, memos, and policies. Search across all documents by keyword, topic, or author. Deep Search returns results at the paragraph level.

Content migration

Extract text from Word documents for import into a new CMS, knowledge base, or documentation system. Structured chunks make mapping straightforward.

Compliance audit

Process policy documents and internal guidelines. Index the chunks so compliance teams can search across the full document library.

Compliance audit

Process policy documents and internal guidelines. Index the chunks so compliance teams can search across the full document library.

Document preview

Use the rendered PDF and thumbnail to display Word document previews in your UI. No client-side rendering or LibreOffice instance needed.

Document preview

Use the rendered PDF and thumbnail to display Word document previews in your UI. No client-side rendering or LibreOffice instance needed.

Invoice and contract processing

Submit Word-format invoices or contracts and get structured field extraction. The API detects the document type the same way it does for PDFs.

Invoice and contract processing

Submit Word-format invoices or contracts and get structured field extraction. The API detects the document type the same way it does for PDFs.

Research and analysis

Extract and chunk research reports, white papers, and analyst notes. Feed them into your agent for summarisation or comparative analysis.

FAQs

What is Exabase?

Exabase is infrastructure for AI agents. It gives your agents memory, versioned file storage, AI deep search, and context automation through a set of APIs. Store what your agent learns, search inside any content type, and keep knowledge bases current automatically. Built for production use. Give your agent precise context and cut your token spend by up to 81%.

Who uses Exabase?

Developers and teams building AI agents, copilots, and RAG applications. If your agent needs to remember things between sessions, store and retrieve files, search across documents and media, or stay up to date without manual maintenance, Exabase handles that infrastructure so you can focus on your product.

Does it handle .doc files (old Word format)?

The API is optimised for .docx (Office Open XML). Older .doc files (binary format) may be supported but .docx is recommended for best results.

Does it extract tables and images from the document?

The API extracts text content, including text from tables. Embedded images are not extracted as separate files, but the rendered PDF preserves the full visual layout.

Does it detect document types (invoices, contracts, resumes)?

Yes. If the Word document contains an invoice, contract, or resume, the API detects the type and populates extraction.document.structured with type-specific fields, just as it does for PDFs.

Can I submit a URL instead of uploading a file?

Yes. Pass a url field in the request body pointing to a publicly accessible DOCX file.

Do I have to poll for results?

No. You can configure a webhook URL and Exabase will POST the full result to your server when processing completes. The webhooks guide covers setup.

What happens if extraction fails?

The job state moves to failed. Call the reprocess endpoint to retry without re-uploading.

How long are files retained?

Stored files are retained for 1 day from job creation, then permanently deleted. Download or copy anything you need before the retention window expires.

Is there an SDK?

Yes. The @exabase/sdk package for Node.js/TypeScript handles file streaming, job polling, and chunk retrieval. Install with npm install @exabase/sdk. Or call the REST API directly from any language.

What other file types does Extract recognise?

PDFs, EPUBs, PPTX, images (with OCR), audio (with transcription), video (with transcription), and web pages. The same POST /v2/extract endpoint handles all of them.

Other tools

Token cost calculator

Link preview API

PDF thumbnail generator

PDF to JSON

Website to JSON

Audio to JSON

Video to JSON

Image to JSON

Invoice to JSON

Contract to JSON

Resume to JSON

EPUB to JSON

DOCX to JSON

PDF to chunks

Image to text

Audio transcription

Video transcription

PDF to Markdown

Website to Markdown

Audio to Markdown

Video to Markdown

Image to Markdown

Invoice to Markdown

Contract to Markdown

Resume to Markdown

Token cost calculator

Link preview API

PDF thumbnail generator

PDF to JSON

Website to JSON

Audio to JSON

Video to JSON

Image to JSON

Invoice to JSON

Contract to JSON

Resume to JSON

EPUB to JSON

DOCX to JSON

PDF to chunks

Image to text

Audio transcription

Video transcription

PDF to Markdown

Website to Markdown

Audio to Markdown

Video to Markdown

Image to Markdown

Invoice to Markdown

Contract to Markdown

Resume to Markdown

Deciding?

Ask your favourite AI about Exabase:

Cut your token spend and give your agent precise context.

Get started in minutes.

Start for free

Read the docs

Cut your token spend and give your agent precise context.

Get started in minutes.

Start for free

Read the docs