PDF-to-Office API

Use the PDF-to-Office API to convert PDF documents to editable Office files. Nutrient DWS Processor API supports these output formats:

DOCX for Microsoft Word
XLSX for Microsoft Excel
PPTX for Microsoft PowerPoint

The /build endpoint handles PDF-to-Office conversion. Add the source PDF as a parts item, and set output.type to the Office format you want.

For signup, pricing, and task-level examples, refer to the PDF-to-Office API task page.

Convert a PDF to Word

The following example converts document.pdf to result.docx:

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer your_api_key_here" \
  -o result.docx \
  --fail \
  -F document=@document.pdf \
  -F instructions='{
      "parts": [
        {
          "file": "document"
        }
      ],
      "output": {
        "type": "docx"
      }
    }'

curl -X POST https://api.nutrient.io/build ^
  -H "Authorization: Bearer your_api_key_here" ^
  -o result.docx ^
  --fail ^
  -F document=@document.pdf ^
  -F instructions="{\"parts\": [{\"file\": \"document\"}], \"output\": {\"type\": \"docx\"}}"

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(
        "document",
        "document.pdf",
        RequestBody.create(
          MediaType.parse("application/pdf"),
          new File("document.pdf")
        )
      )
      .addFormDataPart(
        "instructions",
        new JSONObject()
          .put("parts", new JSONArray()
            .put(new JSONObject()
              .put("file", "document")
            )
          )
          .put("output", new JSONObject()
            .put("type", "docx")
          ).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.docx"),
        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("document", "document.pdf")
        .AddParameter("instructions", new JsonObject
        {
          ["parts"] = new JsonArray
          {
            new JsonObject
            {
              ["file"] = "document"
            }
          },
          ["output"] = new JsonObject
          {
            ["type"] = "docx"
          }
        }.ToString());

      request.AdvancedResponseWriter = (responseStream, response) =>
      {
        if (response.StatusCode == HttpStatusCode.OK)
        {
          using (responseStream)
          {
            using var outputFileWriter = File.OpenWrite("result.docx");
            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: "document"
    }
  ],
  output: {
    type: "docx"
  }
}))
formData.append('document', fs.createReadStream('document.pdf'))

;(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.docx"))
  } 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 = {
    'document': open('document.pdf', 'rb')
  },
  data = {
    'instructions': json.dumps({
      'parts': [
        {
          'file': 'document'
        }
      ],
      'output': {
        'type': 'docx'
      }
    })
  },
  stream = True
)

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

<?php

$FileHandle = fopen('result.docx', '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": "document"
        }
      ],
      "output": {
        "type": "docx"
      }
    }',
    'document' => new CURLFILE('document.pdf')
  ),
  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": "document"
    }
  ],
  "output": {
    "type": "docx"
  }
}
--customboundary
Content-Disposition: form-data; name="document"; filename="document.pdf"
Content-Type: application/pdf

(document data)
--customboundary--

Convert a PDF to Excel

Set output.type to xlsx to convert a PDF to an Excel workbook. Use this instructions object:

{
  "parts": [
    {
      "file": "document"
    }
  ],
  "output": {
    "type": "xlsx"
  }
}

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer your_api_key_here" \
  -o result.xlsx \
  --fail \
  -F document=@document.pdf \
  -F instructions='{
      "parts": [
        {
          "file": "document"
        }
      ],
      "output": {
        "type": "xlsx"
      }
    }'

curl -X POST https://api.nutrient.io/build ^
  -H "Authorization: Bearer your_api_key_here" ^
  -o result.xlsx ^
  --fail ^
  -F document=@document.pdf ^
  -F instructions="{\"parts\": [{\"file\": \"document\"}], \"output\": {\"type\": \"xlsx\"}}"

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(
        "document",
        "document.pdf",
        RequestBody.create(
          MediaType.parse("application/pdf"),
          new File("document.pdf")
        )
      )
      .addFormDataPart(
        "instructions",
        new JSONObject()
          .put("parts", new JSONArray()
            .put(new JSONObject()
              .put("file", "document")
            )
          )
          .put("output", new JSONObject()
            .put("type", "xlsx")
          ).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.xlsx"),
        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("document", "document.pdf")
        .AddParameter("instructions", new JsonObject
        {
          ["parts"] = new JsonArray
          {
            new JsonObject
            {
              ["file"] = "document"
            }
          },
          ["output"] = new JsonObject
          {
            ["type"] = "xlsx"
          }
        }.ToString());

      request.AdvancedResponseWriter = (responseStream, response) =>
      {
        if (response.StatusCode == HttpStatusCode.OK)
        {
          using (responseStream)
          {
            using var outputFileWriter = File.OpenWrite("result.xlsx");
            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: "document"
    }
  ],
  output: {
    type: "xlsx"
  }
}))
formData.append('document', fs.createReadStream('document.pdf'))

;(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.xlsx"))
  } 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 = {
    'document': open('document.pdf', 'rb')
  },
  data = {
    'instructions': json.dumps({
      'parts': [
        {
          'file': 'document'
        }
      ],
      'output': {
        'type': 'xlsx'
      }
    })
  },
  stream = True
)

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

<?php

$FileHandle = fopen('result.xlsx', '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": "document"
        }
      ],
      "output": {
        "type": "xlsx"
      }
    }',
    'document' => new CURLFILE('document.pdf')
  ),
  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": "document"
    }
  ],
  "output": {
    "type": "xlsx"
  }
}
--customboundary
Content-Disposition: form-data; name="document"; filename="document.pdf"
Content-Type: application/pdf

(document data)
--customboundary--

Convert a PDF to PowerPoint

Set output.type to pptx to convert a PDF to a PowerPoint presentation. Use this instructions object:

{
  "parts": [
    {
      "file": "document"
    }
  ],
  "output": {
    "type": "pptx"
  }
}

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer your_api_key_here" \
  -o result.pptx \
  --fail \
  -F document=@document.pdf \
  -F instructions='{
      "parts": [
        {
          "file": "document"
        }
      ],
      "output": {
        "type": "pptx"
      }
    }'

curl -X POST https://api.nutrient.io/build ^
  -H "Authorization: Bearer your_api_key_here" ^
  -o result.pptx ^
  --fail ^
  -F document=@document.pdf ^
  -F instructions="{\"parts\": [{\"file\": \"document\"}], \"output\": {\"type\": \"pptx\"}}"

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(
        "document",
        "document.pdf",
        RequestBody.create(
          MediaType.parse("application/pdf"),
          new File("document.pdf")
        )
      )
      .addFormDataPart(
        "instructions",
        new JSONObject()
          .put("parts", new JSONArray()
            .put(new JSONObject()
              .put("file", "document")
            )
          )
          .put("output", new JSONObject()
            .put("type", "pptx")
          ).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.pptx"),
        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("document", "document.pdf")
        .AddParameter("instructions", new JsonObject
        {
          ["parts"] = new JsonArray
          {
            new JsonObject
            {
              ["file"] = "document"
            }
          },
          ["output"] = new JsonObject
          {
            ["type"] = "pptx"
          }
        }.ToString());

      request.AdvancedResponseWriter = (responseStream, response) =>
      {
        if (response.StatusCode == HttpStatusCode.OK)
        {
          using (responseStream)
          {
            using var outputFileWriter = File.OpenWrite("result.pptx");
            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: "document"
    }
  ],
  output: {
    type: "pptx"
  }
}))
formData.append('document', fs.createReadStream('document.pdf'))

;(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.pptx"))
  } 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 = {
    'document': open('document.pdf', 'rb')
  },
  data = {
    'instructions': json.dumps({
      'parts': [
        {
          'file': 'document'
        }
      ],
      'output': {
        'type': 'pptx'
      }
    })
  },
  stream = True
)

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

<?php

$FileHandle = fopen('result.pptx', '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": "document"
        }
      ],
      "output": {
        "type": "pptx"
      }
    }',
    'document' => new CURLFILE('document.pdf')
  ),
  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": "document"
    }
  ],
  "output": {
    "type": "pptx"
  }
}
--customboundary
Content-Disposition: form-data; name="document"; filename="document.pdf"
Content-Type: application/pdf

(document data)
--customboundary--

Convert a PDF from a URL

For remotely hosted source files, send a JSON request and pass the source URL in parts[].file.url. Use this instructions object:

{
  "parts": [
    {
      "file": {
        "url": "https://example.com/document.pdf"
      }
    }
  ],
  "output": {
    "type": "docx"
  }
}

Shell

Run this request to convert a PDF from a URL:

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "parts": [
      {
        "file": {
          "url": "https://example.com/document.pdf"
        }
      }
    ],
    "output": {
      "type": "docx"
    }
  }' \
  -o result.docx

Convert selected PDF pages

Use parts[].pages to convert only a page range from the source PDF. Page indexes are zero-based, and negative values count from the end of the document.

The following example converts only the first three pages to Word:

{
  "parts": [
    {
      "file": "document",
      "pages": {
        "start": 0,
        "end": 2
      }
    }
  ],
  "output": {
    "type": "docx"
  }
}

The end value is inclusive, so { "start": 0, "end": 2 } includes pages zero, one, and two.

Convert password-protected PDFs

If the source PDF is password-protected, include the password on the part. Use this instructions object:

{
  "parts": [
    {
      "file": "protected_document",
      "password": "document-password"
    }
  ],
  "output": {
    "type": "docx"
  }
}

Nutrient DWS Processor API uses the password only to open the source document for processing.

Choose an output format

Choose the Office output format that matches your downstream workflow.

Output type	File extension	Use when
`docx`	`.docx`	You need editable text, paragraphs, headings, or general document layout in Microsoft Word.
`xlsx`	`.xlsx`	You need spreadsheet-style output, tables, or tabular content in Microsoft Excel.
`pptx`	`.pptx`	You need slide-based output in Microsoft PowerPoint.

PDF-to-Office conversion reconstructs editable Office content from a fixed-layout PDF. Complex layouts, scanned pages, or image-only PDFs may require OCR or manual review, depending on your quality requirements.

Combine PDF-to-Office with other processing

The /build endpoint can assemble or prepare a PDF before it converts the file to Office. For example, you can merge two PDF files and convert the merged output to DOCX.

Use this instructions object to merge two PDFs and convert them to Word:

{
  "parts": [
    {
      "file": "cover"
    },
    {
      "file": "body"
    }
  ],
  "output": {
    "type": "docx"
  }
}

You can also extract selected pages before conversion with parts[].pages.

Reference

A PDF-to-Office request uses the Build API output object with an Office output type:

type OfficeOutput = {
  // Office output file type.
  type: "docx" | "xlsx" | "pptx",
};

type FilePart = {
  // Multipart field name, or a remote URL object.
  file: string | { url: string },

  // Optional password for encrypted input PDFs.
  password?: string,

  // Optional page range to convert.
  pages?: {
    start?: number,
    end?: number,
  },
};

type BuildInstructions = {
  parts: FilePart[],
  output: OfficeOutput,
};

Refer to the build document endpoint API reference to convert PDFs to DOCX, XLSX, or PPTX and combine conversion with page selection or document assembly.

Refer to the Office-to-PDF API guide.
Refer to the PDF-to-image API guide.
Refer to the PDF-to-HTML API guide.
Refer to the PDF-to-Markdown API guide.
Refer to the PDF OCR API guide.
Refer to the PDF merge API guide.
Refer to the PDF split API guide.
Refer to the tools and APIs guide.

PDF-to-Office API

Convert a PDF to Word

Convert a PDF to Excel

Convert a PDF to PowerPoint

Convert a PDF from a URL

Shell

Convert selected PDF pages

Convert password-protected PDFs

Choose an output format

Combine PDF-to-Office with other processing

Reference

Was this helpful?

Help us improve

Thank you for your feedback!

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

PDF-to-Office API

Convert a PDF to Word

Convert a PDF to Excel

Convert a PDF to PowerPoint

Convert a PDF from a URL

Shell

Convert selected PDF pages

Convert password-protected PDFs

Choose an output format

Combine PDF-to-Office with other processing

Reference

Related API reference operations

Related guides

Was this helpful?

Help us improve

Thank you for your feedback!

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