Tools

Image to text API

Extract text from any image. Photos, screenshots, scanned documents, handwritten notes. One API call, structured text back.

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

Extract text from images

Upload an image or submit a URL, get the text back.

{
  "kind": "image",
  "name": "Sprint planning whiteboard",
  "state": "completed",
  "extraction": {
    "common": {
      "mimeType": "image/jpeg",
      "size": 3842048,
      "thumbnail": "https://cdn.exabase.io/...",
      "chunkCount": 4
    },
    "media": {
      "width": 4032,
      "height": 3024,
      "ocr": "Sprint 14 — June 2–13\n\nTo Do\n- Auth token refresh (BE) — 3pts\n- Dashboard filter persistence — 2pts\n- Webhook retry logic — 5pts\n\nIn Progress\n- CSV export performance — Jake\n- Onboarding flow v2 — Maria\n\nDone\n- Rate limiter middleware\n- Billing page redesign"
    }
  }
}

Start for free

Read the docs

What is Exabase's image to text API?

Submit an image to the Exabase Extract API and get the text back. The API runs OCR on the image and returns the extracted text as a single string and as structured chunks you can search and index. JPEG, PNG, WebP, TIFF, BMP, and other major formats are supported.

The same POST /v2/extract endpoint accepts both file uploads and URLs pointing to hosted images. OCR runs on Exabase's infrastructure. No Tesseract installation, no OpenCV, no preprocessing pipeline on your end.

What you get back

The response includes the full OCR text in extraction.media.ocr and the text split into structured chunks. Each chunk has a sequence number and the extracted text. You also get image dimensions (width and height), MIME type, file size, and a CDN-hosted thumbnail. 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 images, it runs OCR and returns the extracted text. For PDFs, it returns text chunks with page numbers and (for recognised document types) structured field extraction. For audio and video, it generates full transcripts with timestamps. 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

Extract text from photos of documents, receipts, whiteboards, labels, and signs. Build a searchable archive of screenshots where every word is indexed. Process business cards and pull out contact details. Digitise handwritten notes so they're searchable alongside typed documents.

Store extracted images as Resources in a Base and the OCR text becomes searchable through Deep Search at the chunk level. Feed the text into a RAG pipeline so your agent can reference what's in the image. Workers can process new images as they arrive, keeping your text index current without manual work.

Beyond OCR

The Extract API returns more than the text in the image. You get image dimensions, MIME type, file size, a CDN-hosted thumbnail, and searchable chunks. 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. The Submitting Jobs guide at https://exabase.io/docs/developer-guide/extraction/submitting-jobs walks through the full flow.

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 an image

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("./whiteboard-photo.jpg"),
  name: "Sprint planning whiteboard",
});

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?.media?.ocr); // full extracted text
  console.log(result.extraction?.common?.chunkCount);
}

One API call. No Tesseract, no OpenCV, no preprocessing.

What you get back

Field

Type

Description

state

string

completed or failed

kind

string

image

extraction.common.mimeType

string

Detected MIME type (e.g. image/jpeg)

extraction.common.size

number

File size in bytes

extraction.common.thumbnail

string

CDN-hosted thumbnail URL

extraction.common.chunkCount

number

Number of text chunks from OCR

extraction.media.width

number

Image width in pixels

extraction.media.height

number

Image height in pixels

extraction.media.ocr

string

Full extracted text

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

Each chunk includes a sequence number and the extracted text.

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 infrastructure to manage

OCR runs on Exabase's infrastructure. No Tesseract installation, no model hosting, no image preprocessing. Submit an image, get text back.

No infrastructure to manage

OCR runs on Exabase's infrastructure. No Tesseract installation, no model hosting, no image preprocessing. Submit an image, get text back.

Dimensions and metadata included

Every response includes image width, height, MIME type, and file size alongside the OCR output. No need to fetch the image separately to get its properties.

Dimensions and metadata included

Every response includes image width, height, MIME type, and file size alongside the OCR output. No need to fetch the image separately to get its properties.

Text as searchable chunks

The extracted text is split into structured chunks, not returned as a raw string you have to parse. Feed them into search indexes or RAG pipelines directly.

Text as searchable chunks

The extracted text is split into structured chunks, not returned as a raw string you have to parse. Feed them into search indexes or RAG pipelines directly.

Handles real-world images

Photos of documents, screenshots, whiteboard captures, handwritten notes, labels, signage. The OCR engine handles common orientations and mixed content.

Handles real-world images

Photos of documents, screenshots, whiteboard captures, handwritten notes, labels, signage. The OCR engine handles common orientations and mixed content.

One API for everything

The same POST /v2/extract endpoint handles video, audio, PDFs, images, and web pages. The response structure adapts to the content type. Learn one API, extract from anything.

One API for everything

The same POST /v2/extract endpoint handles video, audio, PDFs, images, and web pages. The response structure adapts to the content type. Learn one API, extract from anything.

Async processing that scales

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

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. Useful for large files where re-uploading is costly.

Reprocess without re-uploading

If a job fails, call the reprocess endpoint. The API retries using the original file without requiring a new upload. Useful for large files where re-uploading is costly.

Same account for full platform access

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

Same account for full platform access

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

Comparisons

vs Google Cloud Vision OCR

Cloud Vision is a full computer vision platform. OCR is one feature alongside label detection, object detection, face detection, and more. Setup involves GCP project configuration, service accounts, and the Vision SDK. If you only need text extraction, Exabase is one API call with one API key. The OCR output feeds directly into the rest of the platform if you need storage, search, or automation.

vs Tesseract

Tesseract is open-source and free, but running it means installing system dependencies, preprocessing images for better accuracy (deskewing, binarisation, noise reduction), handling edge cases per language, and scaling the infrastructure. Exabase handles all of that. Submit an image, get text back.

vs Tesseract

Tesseract is open-source and free, but running it means installing system dependencies, preprocessing images for better accuracy (deskewing, binarisation, noise reduction), handling edge cases per language, and scaling the infrastructure. Exabase handles all of that. Submit an image, get text back.

vs AWS Textract

Textract extracts text, forms, and tables from images and documents. Setup involves configuring IAM roles, S3 buckets, and the Textract SDK. For straightforward text extraction from images, Exabase is simpler: one endpoint, one API key, no AWS configuration.

vs AWS Textract

Textract extracts text, forms, and tables from images and documents. Setup involves configuring IAM roles, S3 buckets, and the Textract SDK. For straightforward text extraction from images, Exabase is simpler: one endpoint, one API key, no AWS configuration.

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

Document digitisation

Photograph paper documents and extract the text. Store the output as Resources and the content becomes searchable through Deep Search. No manual transcription.

Receipt and label scanning

Extract text from photos of receipts, shipping labels, product labels, and barcodes. Feed the output into expense tracking, inventory, or logistics systems.

Receipt and label scanning

Extract text from photos of receipts, shipping labels, product labels, and barcodes. Feed the output into expense tracking, inventory, or logistics systems.

Screenshot search

Build a searchable archive of screenshots. Every word in every image is extracted and indexed. Users search by text content instead of scrolling through files.

Screenshot search

Build a searchable archive of screenshots. Every word in every image is extracted and indexed. Users search by text content instead of scrolling through files.

Whiteboard capture

Extract text from photos of whiteboards and sticky notes after meetings. Store the output alongside the original image for reference.

Whiteboard capture

Extract text from photos of whiteboards and sticky notes after meetings. Store the output alongside the original image for reference.

Business card processing

Extract names, phone numbers, email addresses, and company names from business card photos. Feed the text into your CRM or contact database.

Accessibility

Generate text alternatives for images that contain text. The OCR output provides the raw material for alt text, screen reader descriptions, or searchable captions.

Accessibility

Generate text alternatives for images that contain text. The OCR output provides the raw material for alt text, screen reader descriptions, or searchable captions.

Handwritten note indexing

Extract text from handwritten notes and make them searchable. Accuracy depends on handwriting legibility, but typed and printed text in the same image is captured reliably.

Handwritten note indexing

Extract text from handwritten notes and make them searchable. Accuracy depends on handwriting legibility, but typed and printed text in the same image is captured reliably.

Product catalogue processing

Extract specifications, descriptions, and model numbers from product images. Use the text to populate catalogue fields or power product search.

Product catalogue processing

Extract specifications, descriptions, and model numbers from product images. Use the text to populate catalogue fields or power product search.

Insurance and claims

Process photos submitted with claims: damage reports, repair estimates, receipts. Extract the text and make it searchable for adjusters and auditors.

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.

How accurate is the OCR?

Accuracy depends on image quality, text size, contrast, and orientation. Clean photos of printed or typed text produce the most reliable results. Handwriting recognition works but accuracy varies with legibility. For best results, ensure the text in the image is reasonably upright and legible.

What image formats are supported?

JPEG, PNG, WebP, TIFF, BMP, and other major image formats. The API auto-detects the content type and processes accordingly.

Does it handle rotated or skewed text?

The OCR engine handles common orientations and moderate skew. For best results, images with text that's roughly upright will produce the most accurate output.

What if the image has no text?

The API still returns image metadata (dimensions, MIME type, file size, thumbnail). The OCR field will be empty and chunk count will be zero.

Does it handle handwriting?

Yes, with caveats. Printed and typed text is extracted reliably. Handwriting recognition works but accuracy depends on legibility. Neat handwriting on a clean background produces the best results.

Can I submit a URL instead of uploading a file?

Yes. Pass a url field in the request body pointing to a publicly accessible image. Exabase fetches and processes it.

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. You can call the reprocess endpoint to retry without re-uploading the original file.

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.

Can I use the extracted text with other Exabase features?

Yes. Store extracted images as a Resource in a Base and the OCR text becomes searchable through Deep Search. Extract key facts into Memory so your agent retains what it read. Workers can re-extract updated images on a schedule.

How is this different from the Image to JSON tool?

The Image to JSON page covers the full extraction response: metadata, dimensions, thumbnail, OCR text, and chunks. Image to Text focuses specifically on the OCR output. Same underlying API, different emphasis.

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 content types does Extract support?

PDFs, audio files (with transcription), video files (with transcription), web pages, and documents. The same POST /v2/extract endpoint handles all of them. See the PDF to JSON, Audio Transcription, Video Transcription, and Website to JSON tool pages.

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

PDF to chunks

Image to text

Audio transcription

Video transcription

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

PDF to chunks

Image to text

Audio transcription

Video transcription

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