Free PDF OCR Tool

More than 1000 enterprises extract text and tables from PDFs with our free online PDF OCR Tool.

Data security comes first – We'll never sell or share your data. For more details, here’s our Privacy Policy

Upload Images or PDF Files

Select files from your computer, or just drag and drop into the upload box. Supports PDF, PNG, JPG files.

OCR works on PDF File

Our PDF OCR tool automatically recognizes the content in your file and converts it into text that you can then edit.

Download text file

Download your converted text file within seconds.

DOCUMENTS SUPPORTED
Invoices, Receipts, Bills
Delivery Notes, Purchase Orders, Bill of Lading
ID cards, Driver’s License, Passports
W2s, Tax documents
Bank Statements, Loan Approval documents
Real Estate Documents
..and many more!
Capture intelligence from documents

The world’s fastest, most powerful and easy-to-use PDF OCR APIs

rated 4.9 on g2 and on capterra (2022)

Our customers love us—see what they have to say

AP Team
Happy jewellers

“Working with NanoNets has been superfluid. They understand the requirements of SMBs very well, and were quickly able to suggest workflow automations using their solution. The other important thing about NanoNets was that it did not disturb the operations for any employee, instead made their work easier.”

Ryan Hess
Head of Accounts Payable, ACM SERVICES

“I would recommend NanoNets over other services because of their friendly team. I knew integration with our current stubborn accounting software was going to be difficult, but the NanoNets team assured me they could make it happen for us. They delivered better than I could have expected. I have built a relationship with Nano which is an important ideal of ACM and it feels now as if they are part of the family.”

M. Aflah
pt, solusi aplikasi (indonesia)

Nanonets helped us deploy the data capture workflow with Quickbooks < 7 days from the contract signing date. This has directly impacted the finance team, who can process 50% more invoices at the same time without hiring more people.

We are impressed with the intelligence in the product when it comes to data extraction. This opens up for many new areas where we can help our customers, like detection of fraud. We have been having a tight and transparent dialogue with Nanonets. Our customers are very pleased with the product as well as the technical support we together with Nanonets have been able to provide.

Per Defalva

Founder, DigitalEngine (Sweden), ex-CIO PwC Sweden

automate your PDF OCR workflow

Try a smarter way to OCR PDFs and Images and extract data in seconds.

How we compare

Why Nanonets PDF OCR is better ?

Traditional OCR Tools
Data Formatting
High savings
Nil or low training data
High training data
High training data
Receive documents from multiple channels
Amount of training data needed
Self-learning AI
No Template setup required
IT / API friendly
Multiple export options
Cost and Time Savings

PDF OCR API

Copy integration code

Browse libraries for different programming languages and mobile platforms.

Choose your language

import requests import base64 url = "https://app.nanonets.com/api/v2/OCR/FullText" payload={'urls': ['MY_IMAGE_URL']} files=[ ('file',('FILE_NAME',open('FILE_PATH','rb'),'application/pdf')) ] headers = {} response = requests.request("POST", url, headers=headers, data=payload, files=files, auth=requests.auth.HTTPBasicAuth('REPLACE_API_KEY', '')) print(response.text)
var axios = require('axios'); var FormData = require('form-data'); var fs = require('fs'); var data = new FormData(); data.apend('urls','FILE_URL') data.append('file', fs.createReadStream('FILE_PATH')); var config = { method: 'post', url: 'https://app.nanonets.com/api/v2/OCR/FullText', headers: { 'Authorization': 'Basic ' + Buffer.from("REPLACE_API_KEY" + ":").toString('base64'), ...data.getHeaders() }, data : data }; axios(config) .then(function (response) { console.log(JSON.stringify(response.data)); }) .catch(function (error) { console.log(error); });
var axios = require('axios'); var FormData = require('form-data'); var fs = require('fs'); var data = new FormData(); data.apend('urls','FILE_URL') data.append('file', fs.createReadStream('FILE_PATH')); var config = { method: 'post', url: 'https://app.nanonets.com/api/v2/OCR/FullText', headers: { 'Authorization': 'Basic ' + Buffer.from("REPLACE_API_KEY" + ":").toString('base64'), ...data.getHeaders() }, data : data }; axios(config) .then(function (response) { console.log(JSON.stringify(response.data)); }) .catch(function (error) { console.log(error); });
var client = new RestClient("https://app.nanonets.com/api/v2/OCR/FullText"); client.Timeout = -1; var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Basic " + Convert.ToBase64String(Encoding.Default.GetBytes("REPLACE_YOUR_API_KEY:"))); request.AddFile("file", "FILE_PATH"); IRestResponse response = client.Execute(request); Console.WriteLine(response.Content);
curl --location --request POST 'https://app.nanonets.com/api/v2/OCR/FullText' \ -u 'REPLACE_API_KEY:' \ --form 'file=@"FILE_PATH"'
Get your free API key

Once you create your account, click on My Account > API Keys to get your key. This key will allow you to authenticate API requests.

1abcd000-ABCab1BCd00a00abc1AbcDeF
Get API Key
Want to Use our Python Package ?

Our Python Library gives you added control and options to perform OCR and extract text and tabular results in desired formats instantly.

Python Library

Security certifications

Security is a priority at Nanonets

World Class Training and Support
Highest security standards
99.95% Uptime
Strict Privacy Policies
GDPR
COMPLIANT
SOC 2
CErtified
HIPPA
COMPLIANT

Key Features

User-friendly online OCR interface
Convert .jpg, .bmp, .png or .PDFs to text
No registration or signup needed
Free, low latency OCR API with unlimited requests
State of the art OCR accuracy - best in class
Supports 42+ languages for text recognition
Secure conversion - all data is removed
Over 1 billion requests processed

PDF OCR FAQs

Can I convert documents and images to Excel ?
Can I integrate your PDF OCR API in code?