PDF OCR API

This guide explains how to use all the functionality the OCR API provides.

Basic OCR usage

The OCR API enables you to take files in any supported format and extract text to make it selectable and searchable. This is useful for images and scanned documents. To learn more about OCR itself, refer to the Wikipedia article on optical character recognition(opens in a new tab).

To run OCR on a single image file, add a page1.jpg file to the same folder as your code. You can use any image containing text, or use the sample page.

Run the code to get a result.pdf with your page OCRed. The example sets the OCR language to English. If your content is in a different language, update the language property accordingly. Refer to the supported languages section for a list of all available languages.

Below is the code to perform OCR:

curl -X POST https://api.nutrient.io/processor/ocr \
  -H "Authorization: Bearer your_api_key_here" \
  -o result.pdf \
  --fail \
  -F file=@page1.jpg \
  -F data='{
      "language": "english"
    }'

curl -X POST https://api.nutrient.io/processor/ocr ^
  -H "Authorization: Bearer your_api_key_here" ^
  -o result.pdf ^
  --fail ^
  -F file=@page1.jpg ^
  -F data="{\"language\": \"english\"}"

package com.example.pspdfkit;

import java.io.File;
import java.io.IOException;
import java.nio.file.FileSystems;
import java.nio.file.Files;
import java.nio.file.StandardCopyOption;

import org.json.JSONArray;
import org.json.JSONObject;

import okhttp3.MediaType;
import okhttp3.MultipartBody;
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.RequestBody;
import okhttp3.Response;

public final class PspdfkitApiExample {
  public static void main(final String[] args) throws IOException {
    final RequestBody body = new MultipartBody.Builder()
      .setType(MultipartBody.FORM)
      .addFormDataPart(
        "file",
        "page1.jpg",
        RequestBody.create(
          MediaType.parse("image/jpeg"),
          new File("page1.jpg")
        )
      )
      .addFormDataPart(
        "data",
        new JSONObject()
          .put("language", "english").toString()
      )
      .build();

    final Request request = new Request.Builder()
      .url("https://api.nutrient.io/processor/ocr")
      .method("POST", body)
      .addHeader("Authorization", "Bearer your_api_key_here")
      .build();

    final OkHttpClient client = new OkHttpClient()
      .newBuilder()
      .build();

    final Response response = client.newCall(request).execute();

    if (response.isSuccessful()) {
      Files.copy(
        response.body().byteStream(),
        FileSystems.getDefault().getPath("result.pdf"),
        StandardCopyOption.REPLACE_EXISTING
      );
    } else {
      // Handle the error.
      throw new IOException(response.body().string());
    }
  }
}

using System;
using System.IO;
using System.Net;
using RestSharp;

namespace PspdfkitApiDemo
{
  class Program
  {
    static void Main(string[] args)
    {
      var client = new RestClient("https://api.nutrient.io/processor/ocr");

      var request = new RestRequest(Method.POST)
        .AddHeader("Authorization", "Bearer your_api_key_here")
        .AddFile("file", "page1.jpg")
        .AddParameter("data", new JsonObject
        {
          ["language"] = "english"
        }.ToString());

      request.AdvancedResponseWriter = (responseStream, response) =>
      {
        if (response.StatusCode == HttpStatusCode.OK)
        {
          using (responseStream)
          {
            using var outputFileWriter = File.OpenWrite("result.pdf");
            responseStream.CopyTo(outputFileWriter);
          }
        }
        else
        {
          var responseStreamReader = new StreamReader(responseStream);
          Console.Write(responseStreamReader.ReadToEnd());
        }
      };

      client.Execute(request);
    }
  }
}

// This code requires Node.js. Do not run this code directly in a web browser.

const axios = require('axios')
const FormData = require('form-data')
const fs = require('fs')

const formData = new FormData()
formData.append('data', JSON.stringify({
  language: "english"
}))
formData.append('file', fs.createReadStream('page1.jpg'))

;(async () => {
  try {
    const response = await axios.post('https://api.nutrient.io/processor/ocr', formData, {
      headers: formData.getHeaders({
        'Authorization': 'Bearer your_api_key_here'
      }),
      responseType: "stream"
    })

    response.data.pipe(fs.createWriteStream("result.pdf"))
  } catch (e) {
    const errorString = await streamToString(e.response.data)
    console.log(errorString)
  }
})()

function streamToString(stream) {
  const chunks = []
  return new Promise((resolve, reject) => {
    stream.on("data", (chunk) => chunks.push(Buffer.from(chunk)))
    stream.on("error", (err) => reject(err))
    stream.on("end", () => resolve(Buffer.concat(chunks).toString("utf8")))
  })
}

import requests
import json

response = requests.request(
  'POST',
  'https://api.nutrient.io/processor/ocr',
  headers = {
    'Authorization': 'Bearer your_api_key_here'
  },
  files = {
    'file': open('page1.jpg', 'rb')
  },
  data = {
    'data': json.dumps({
      'language': 'english'
    })
  },
  stream = True
)

if response.ok:
  with open('result.pdf', 'wb') as fd:
    for chunk in response.iter_content(chunk_size=8096):
      fd.write(chunk)
else:
  print(response.text)
  exit()

<?php

$FileHandle = fopen('result.pdf', 'w+');

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://api.nutrient.io/processor/ocr',
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_POSTFIELDS => array(
    'data' => '{
      "language": "english"
    }',
    'file' => new CURLFILE('page1.jpg')
  ),
  CURLOPT_HTTPHEADER => array(
    'Authorization: Bearer your_api_key_here'
  ),
  CURLOPT_FILE => $FileHandle,
));

$response = curl_exec($curl);

curl_close($curl);

fclose($FileHandle);

POST https://api.nutrient.io/processor/ocr HTTP/1.1
Content-Type: multipart/form-data; boundary=--customboundary
Authorization: Bearer your_api_key_here

--customboundary
Content-Disposition: form-data; name="data"
Content-Type: application/json

{
  "language": "english"
}
--customboundary
Content-Disposition: form-data; name="file"; filename="page1.jpg"
Content-Type: image/jpeg

(file data)
--customboundary--

Running OCR on multiple pages

While running OCR on a single page is useful, often you’ll have a folder full of scanned pages that you want to both run OCR on and merge into a single searchable PDF.

Pass in multiple images — one for each page in your request — and Nutrient DWS Processor API will merge all of them into a PDF before running OCR on it.

Add more files in the same folder as your code and run the updated code. You can duplicate and rename the existing file you have, or you can add some other images containing text.

Below is the code to perform OCR on multiple pages:

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer your_api_key_here" \
  -o result.pdf \
  --fail \
  -F page1.jpg=@/path/to/page1.jpg \
  -F page2.jpg=@/path/to/page2.jpg \
  -F page3.jpg=@/path/to/page3.jpg \
  -F page4.jpg=@/path/to/page4.jpg \
  -F instructions='{
      "parts": [
        {
          "file": "page1.jpg"
        },
        {
          "file": "page2.jpg"
        },
        {
          "file": "page3.jpg"
        },
        {
          "file": "page4.jpg"
        }
      ],
      "actions": [
        {
          "type": "ocr",
          "language": "english"
        }
      ]
    }'

curl -X POST https://api.nutrient.io/build ^
  -H "Authorization: Bearer your_api_key_here" ^
  -o result.pdf ^
  --fail ^
  -F page1.jpg=@/path/to/page1.jpg ^
  -F page2.jpg=@/path/to/page2.jpg ^
  -F page3.jpg=@/path/to/page3.jpg ^
  -F page4.jpg=@/path/to/page4.jpg ^
  -F instructions="{\"parts\": [{\"file\": \"page1.jpg\"}, {\"file\": \"page2.jpg\"}, {\"file\": \"page3.jpg\"}, {\"file\": \"page4.jpg\"}], \"actions\": [{\"type\": \"ocr\", \"language\": \"english\"}]}"

package com.example.pspdfkit;

import java.io.File;
import java.io.IOException;
import java.nio.file.FileSystems;
import java.nio.file.Files;
import java.nio.file.StandardCopyOption;

import org.json.JSONArray;
import org.json.JSONObject;

import okhttp3.MediaType;
import okhttp3.MultipartBody;
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.RequestBody;
import okhttp3.Response;

public final class PspdfkitApiExample {
  public static void main(final String[] args) throws IOException {
    final RequestBody body = new MultipartBody.Builder()
      .setType(MultipartBody.FORM)
      .addFormDataPart(
        "page1.jpg",
        "/path/to/page1.jpg",
        RequestBody.create(
          MediaType.parse("image/jpeg"),
          new File("/path/to/page1.jpg")
        )
      )
      .addFormDataPart(
        "page2.jpg",
        "/path/to/page2.jpg",
        RequestBody.create(
          MediaType.parse("image/jpeg"),
          new File("/path/to/page2.jpg")
        )
      )
      .addFormDataPart(
        "page3.jpg",
        "/path/to/page3.jpg",
        RequestBody.create(
          MediaType.parse("image/jpeg"),
          new File("/path/to/page3.jpg")
        )
      )
      .addFormDataPart(
        "page4.jpg",
        "/path/to/page4.jpg",
        RequestBody.create(
          MediaType.parse("image/jpeg"),
          new File("/path/to/page4.jpg")
        )
      )
      .addFormDataPart(
        "instructions",
        new JSONObject()
          .put("parts", new JSONArray()
            .put(new JSONObject()
              .put("file", "page1.jpg")
            )
            .put(new JSONObject()
              .put("file", "page2.jpg")
            )
            .put(new JSONObject()
              .put("file", "page3.jpg")
            )
            .put(new JSONObject()
              .put("file", "page4.jpg")
            )
          )
          .put("actions", new JSONArray()
            .put(new JSONObject()
              .put("type", "ocr")
              .put("language", "english")
            )
          ).toString()
      )
      .build();

    final Request request = new Request.Builder()
      .url("https://api.nutrient.io/build")
      .method("POST", body)
      .addHeader("Authorization", "Bearer your_api_key_here")
      .build();

    final OkHttpClient client = new OkHttpClient()
      .newBuilder()
      .build();

    final Response response = client.newCall(request).execute();

    if (response.isSuccessful()) {
      Files.copy(
        response.body().byteStream(),
        FileSystems.getDefault().getPath("result.pdf"),
        StandardCopyOption.REPLACE_EXISTING
      );
    } else {
      // Handle the error.
      throw new IOException(response.body().string());
    }
  }
}

using System;
using System.IO;
using System.Net;
using RestSharp;

namespace PspdfkitApiDemo
{
  class Program
  {
    static void Main(string[] args)
    {
      var client = new RestClient("https://api.nutrient.io/build");

      var request = new RestRequest(Method.POST)
        .AddHeader("Authorization", "Bearer your_api_key_here")
        .AddFile("page1.jpg", "/path/to/page1.jpg")
        .AddFile("page2.jpg", "/path/to/page2.jpg")
        .AddFile("page3.jpg", "/path/to/page3.jpg")
        .AddFile("page4.jpg", "/path/to/page4.jpg")
        .AddParameter("instructions", new JsonObject
        {
          ["parts"] = new JsonArray
          {
            new JsonObject
            {
              ["file"] = "page1.jpg"
            },
            new JsonObject
            {
              ["file"] = "page2.jpg"
            },
            new JsonObject
            {
              ["file"] = "page3.jpg"
            },
            new JsonObject
            {
              ["file"] = "page4.jpg"
            }
          },
          ["actions"] = new JsonArray
          {
            new JsonObject
            {
              ["type"] = "ocr",
              ["language"] = "english"
            }
          }
        }.ToString());

      request.AdvancedResponseWriter = (responseStream, response) =>
      {
        if (response.StatusCode == HttpStatusCode.OK)
        {
          using (responseStream)
          {
            using var outputFileWriter = File.OpenWrite("result.pdf");
            responseStream.CopyTo(outputFileWriter);
          }
        }
        else
        {
          var responseStreamReader = new StreamReader(responseStream);
          Console.Write(responseStreamReader.ReadToEnd());
        }
      };

      client.Execute(request);
    }
  }
}

// This code requires Node.js. Do not run this code directly in a web browser.

const axios = require('axios')
const FormData = require('form-data')
const fs = require('fs')

const formData = new FormData()
formData.append('instructions', JSON.stringify({
  parts: [
    {
      file: "page1.jpg"
    },
    {
      file: "page2.jpg"
    },
    {
      file: "page3.jpg"
    },
    {
      file: "page4.jpg"
    }
  ],
  actions: [
    {
      type: "ocr",
      language: "english"
    }
  ]
}))
formData.append('page1.jpg', fs.createReadStream('/path/to/page1.jpg'))
formData.append('page2.jpg', fs.createReadStream('/path/to/page2.jpg'))
formData.append('page3.jpg', fs.createReadStream('/path/to/page3.jpg'))
formData.append('page4.jpg', fs.createReadStream('/path/to/page4.jpg'))

;(async () => {
  try {
    const response = await axios.post('https://api.nutrient.io/build', formData, {
      headers: formData.getHeaders({
        'Authorization': 'Bearer your_api_key_here'
      }),
      responseType: "stream"
    })

    response.data.pipe(fs.createWriteStream("result.pdf"))
  } catch (e) {
    const errorString = await streamToString(e.response.data)
    console.log(errorString)
  }
})()

function streamToString(stream) {
  const chunks = []
  return new Promise((resolve, reject) => {
    stream.on("data", (chunk) => chunks.push(Buffer.from(chunk)))
    stream.on("error", (err) => reject(err))
    stream.on("end", () => resolve(Buffer.concat(chunks).toString("utf8")))
  })
}

import requests
import json

response = requests.request(
  'POST',
  'https://api.nutrient.io/build',
  headers = {
    'Authorization': 'Bearer your_api_key_here'
  },
  files = {
    'page1.jpg': open('/path/to/page1.jpg', 'rb'),
    'page2.jpg': open('/path/to/page2.jpg', 'rb'),
    'page3.jpg': open('/path/to/page3.jpg', 'rb'),
    'page4.jpg': open('/path/to/page4.jpg', 'rb')
  },
  data = {
    'instructions': json.dumps({
      'parts': [
        {
          'file': 'page1.jpg'
        },
        {
          'file': 'page2.jpg'
        },
        {
          'file': 'page3.jpg'
        },
        {
          'file': 'page4.jpg'
        }
      ],
      'actions': [
        {
          'type': 'ocr',
          'language': 'english'
        }
      ]
    })
  },
  stream = True
)

if response.ok:
  with open('result.pdf', 'wb') as fd:
    for chunk in response.iter_content(chunk_size=8096):
      fd.write(chunk)
else:
  print(response.text)
  exit()

<?php

$FileHandle = fopen('result.pdf', 'w+');

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://api.nutrient.io/build',
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_POSTFIELDS => array(
    'instructions' => '{
      "parts": [
        {
          "file": "page1.jpg"
        },
        {
          "file": "page2.jpg"
        },
        {
          "file": "page3.jpg"
        },
        {
          "file": "page4.jpg"
        }
      ],
      "actions": [
        {
          "type": "ocr",
          "language": "english"
        }
      ]
    }',
    'page1.jpg' => new CURLFILE('/path/to/page1.jpg'),
    'page2.jpg' => new CURLFILE('/path/to/page2.jpg'),
    'page3.jpg' => new CURLFILE('/path/to/page3.jpg'),
    'page4.jpg' => new CURLFILE('/path/to/page4.jpg')
  ),
  CURLOPT_HTTPHEADER => array(
    'Authorization: Bearer your_api_key_here'
  ),
  CURLOPT_FILE => $FileHandle,
));

$response = curl_exec($curl);

curl_close($curl);

fclose($FileHandle);

POST https://api.nutrient.io/build HTTP/1.1
Content-Type: multipart/form-data; boundary=--customboundary
Authorization: Bearer your_api_key_here

--customboundary
Content-Disposition: form-data; name="instructions"
Content-Type: application/json

{
  "parts": [
    {
      "file": "page1.jpg"
    },
    {
      "file": "page2.jpg"
    },
    {
      "file": "page3.jpg"
    },
    {
      "file": "page4.jpg"
    }
  ],
  "actions": [
    {
      "type": "ocr",
      "language": "english"
    }
  ]
}
--customboundary
Content-Disposition: form-data; name="page1.jpg"; filename="/path/to/page1.jpg"
Content-Type: image/jpeg

(page1.jpg data)
--customboundary
Content-Disposition: form-data; name="page2.jpg"; filename="/path/to/page2.jpg"
Content-Type: image/jpeg

(page2.jpg data)
--customboundary
Content-Disposition: form-data; name="page3.jpg"; filename="/path/to/page3.jpg"
Content-Type: image/jpeg

(page3.jpg data)
--customboundary
Content-Disposition: form-data; name="page4.jpg"; filename="/path/to/page4.jpg"
Content-Type: image/jpeg

(page4.jpg data)
--customboundary--

Supported languages

The OCR action supports more than 80 languages for text extraction. You can specify languages using one of the following:

Full language name (lowercase, e.g. english, german) — available for commonly used languages
ISO 639-2 language code (e.g. eng, deu) — available for all languages
ISO 639-2 language code with variant (e.g. chi_sim_vert or deu_frak)

Description	Language code	Full language name
🇿🇦 Afrikaans	`afr`
🇦🇱 Albanian	`sqi`
🇪🇹 Amharic	`amh`
🇸🇦 Arabic	`ara`
🇦🇲 Armenian	`hye`
🇮🇳 Assamese	`asm`
🇦🇿 Azerbaijani	`aze`
🇦🇿 Azerbaijani — Cyrillic	`aze_cyrl`
🇪🇸 Basque	`eus`
🇧🇾 Belarusian	`bel`
🇧🇩 Bengali	`ben`
🇧🇦 Bosnian	`bos`
🇫🇷 Breton	`bre`
🇧🇬 Bulgarian	`bul`
🇲🇲 Burmese	`mya`
🇪🇸 Catalan; Valencian	`cat`
🇵🇭 Cebuano	`ceb`
🇰🇭 Central Khmer	`khm`
🇺🇸 Cherokee	`chr`
🇨🇳 Chinese — Simplified	`chi_sim`
🇨🇳 Chinese — Simplified (Vertical)	`chi_sim_vert`
🇹🇼 Chinese — Traditional	`chi_tra`
🇹🇼 Chinese — Traditional (Vertical)	`chi_tra_vert`
🇫🇷 Corsican	`cos`
🇭🇷 Croatian	`hrv`	croatian
🇨🇿 Czech	`ces`	czech
🇩🇰 Danish	`dan`	danish
🇩🇰 Danish — Fraktur	`dan_frak`
🇲🇻 Dhivehi; Maldivian	`div`
🇳🇱 Dutch; Flemish	`nld`	dutch
🇧🇹 Dzongkha	`dzo`
🇬🇧 English	`eng`	english
🇬🇧 English, Middle (1100–1500)	`enm`
Esperanto	`epo`
🇪🇪 Estonian	`est`
🇫🇴 Faroese	`fao`
🇵🇭 Filipino	`fil`
🇫🇮 Finnish	`fin`	finnish
🇫🇷 French	`fra`	french
🇫🇷 French, Middle (ca. 1400–1600)	`frm`
🇪🇸 Galician	`glg`
🇬🇪 Georgian	`kat`
🇬🇪 Georgian — Old	`kat_old`
🇩🇪 German	`deu`	german
🇩🇪 German — Fraktur	`deu_frak`
🇩🇪 German Fraktur	`frk`
🇬🇷 Greek, Ancient	`grc`
🇬🇷 Greek, Modern	`ell`
🇮🇳 Gujarati	`guj`
🇭🇹 Haitian; Haitian Creole	`hat`
🇮🇱 Hebrew	`heb`
🇮🇳 Hindi	`hin`
🇭🇺 Hungarian	`hun`
🇮🇸 Icelandic	`isl`
🇮🇩 Indonesian	`ind`	indonesian
🇨🇦 Inuktitut	`iku`
🇮🇪 Irish	`gle`
🇮🇹 Italian	`ita`	italian
🇮🇹 Italian — Old	`ita_old`
🇯🇵 Japanese	`jpn`
🇯🇵 Japanese (Vertical)	`jpn_vert`
🇮🇩 Javanese	`jav`
🇮🇳 Kannada	`kan`
🇰🇿 Kazakh	`kaz`
🇰🇬 Kirghiz; Kyrgyz	`kir`
🇰🇷 Korean	`kor`
🇰🇷 Korean (Vertical)	`kor_vert`
🇮🇶 Kurdish	`kur`
🇹🇷 Kurmanji (Kurdish)	`kmr`
🇱🇦 Lao	`lao`
🇻🇦 Latin	`lat`
🇱🇻 Latvian	`lav`
🇱🇹 Lithuanian	`lit`
🇱🇺 Luxembourgish	`ltz`
🇲🇰 Macedonian	`mkd`
🇲🇾 Malay	`msa`	malay
🇮🇳 Malayalam	`mal`
🇲🇹 Maltese	`mlt`
🇳🇿 Maori	`mri`
🇮🇳 Marathi	`mar`
Math/equation detection	`equ`
🇲🇳 Mongolian	`mon`
🇳🇵 Nepali	`nep`
🇳🇴 Norwegian	`nor`	norwegian
🇫🇷 Occitan	`oci`
🇮🇳 Oriya	`ori`
🇮🇳 Panjabi; Punjabi	`pan`
🇮🇷 Persian	`fas`
🇵🇱 Polish	`pol`	polish
🇵🇹 Portuguese	`por`	portuguese
🇦🇫 Pushto; Pashto	`pus`
🇵🇪 Quechua	`que`
🇷🇴 Romanian; Moldavian	`ron`
🇷🇺 Russian	`rus`
🇮🇳 Sanskrit	`san`
🇬🇧 Scottish Gaelic	`gla`
🇷🇸 Serbian	`srp`	serbian
🇷🇸 Serbian – Latin	`srp_latn`
🇵🇰 Sindhi	`snd`
🇱🇰 Sinhala; Sinhalese	`sin`
🇸🇰 Slovak	`slk`	slovak
🇸🇰 Slovak – Fraktur	`slk_frak`
🇸🇮 Slovenian	`slv`	slovenian
🇪🇸 Spanish; Castilian	`spa`	spanish
🇪🇸 Spanish – Old	`spa_old`
🇮🇩 Sundanese	`sun`
🇰🇪 Swahili	`swa`
🇸🇪 Swedish	`swe`	swedish
🇸🇾 Syriac	`syr`
🇵🇭 Tagalog	`tgl`
🇹🇯 Tajik	`tgk`
🇮🇳 Tamil	`tam`
🇷🇺 Tatar	`tat`
🇮🇳 Telugu	`tel`
🇹🇭 Thai	`tha`
🇨🇳 Tibetan	`bod`
🇪🇷 Tigrinya	`tir`
🇹🇴 Tonga	`ton`
🇹🇷 Turkish	`tur`	turkish
🇨🇳 Uighur; Uyghur	`uig`
🇺🇦 Ukrainian	`ukr`
🇵🇰 Urdu	`urd`
🇺🇿 Uzbek	`uzb`
🇺🇿 Uzbek - Cyrillic	`uzb_cyrl`
🇻🇳 Vietnamese	`vie`
🇬🇧 Welsh	`cym`
🇳🇱 Western Frisian	`fry`
🇮🇱 Yiddish	`yid`
🇳🇬 Yoruba	`yor`

PDF OCR API

Basic OCR usage

Running OCR on multiple pages

Supported languages

Was this helpful?

Help us improve

Thank you for your feedback!

Something went wrong. Please try again or let us know.