Convert document to text
curl --request POST \
--url https://app.dumplingai.com/api/v1/doc-to-text \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"inputMethod": "url",
"file": "https://example.com/report.pdf",
"pages": "1-3,5"
}
'import requests
url = "https://app.dumplingai.com/api/v1/doc-to-text"
payload = {
"inputMethod": "url",
"file": "https://example.com/report.pdf",
"pages": "1-3,5"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({inputMethod: 'url', file: 'https://example.com/report.pdf', pages: '1-3,5'})
};
fetch('https://app.dumplingai.com/api/v1/doc-to-text', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://app.dumplingai.com/api/v1/doc-to-text",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'inputMethod' => 'url',
'file' => 'https://example.com/report.pdf',
'pages' => '1-3,5'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://app.dumplingai.com/api/v1/doc-to-text"
payload := strings.NewReader("{\n \"inputMethod\": \"url\",\n \"file\": \"https://example.com/report.pdf\",\n \"pages\": \"1-3,5\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://app.dumplingai.com/api/v1/doc-to-text")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"inputMethod\": \"url\",\n \"file\": \"https://example.com/report.pdf\",\n \"pages\": \"1-3,5\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://app.dumplingai.com/api/v1/doc-to-text")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"inputMethod\": \"url\",\n \"file\": \"https://example.com/report.pdf\",\n \"pages\": \"1-3,5\"\n}"
response = http.request(request)
puts response.read_body{
"text": "<string>"
}{
"error": "<string>"
}{
"error": "<string>"
}Document Processing
Doc to Text
Convert documents such as PDFs, PowerPoints, or Word files into plain text.
POST
/
api
/
v1
/
doc-to-text
Convert document to text
curl --request POST \
--url https://app.dumplingai.com/api/v1/doc-to-text \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"inputMethod": "url",
"file": "https://example.com/report.pdf",
"pages": "1-3,5"
}
'import requests
url = "https://app.dumplingai.com/api/v1/doc-to-text"
payload = {
"inputMethod": "url",
"file": "https://example.com/report.pdf",
"pages": "1-3,5"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({inputMethod: 'url', file: 'https://example.com/report.pdf', pages: '1-3,5'})
};
fetch('https://app.dumplingai.com/api/v1/doc-to-text', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://app.dumplingai.com/api/v1/doc-to-text",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'inputMethod' => 'url',
'file' => 'https://example.com/report.pdf',
'pages' => '1-3,5'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://app.dumplingai.com/api/v1/doc-to-text"
payload := strings.NewReader("{\n \"inputMethod\": \"url\",\n \"file\": \"https://example.com/report.pdf\",\n \"pages\": \"1-3,5\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://app.dumplingai.com/api/v1/doc-to-text")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"inputMethod\": \"url\",\n \"file\": \"https://example.com/report.pdf\",\n \"pages\": \"1-3,5\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://app.dumplingai.com/api/v1/doc-to-text")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"inputMethod\": \"url\",\n \"file\": \"https://example.com/report.pdf\",\n \"pages\": \"1-3,5\"\n}"
response = http.request(request)
puts response.read_body{
"text": "<string>"
}{
"error": "<string>"
}{
"error": "<string>"
}Description
This endpoint converts PDF or DOCX documents into plain text. It supports input via URL or base64-encoded file content.Endpoint
POST https://app.dumplingai.com/api/v1/doc-to-text
Headers
- Content-Type:
application/json - Authorization: Bearer
<API_KEY>(required)
Request Body
{
"inputMethod": "string", // Required. Either "url" or "base64".
"file": "string", // Required. URL or base64-encoded file content.
"pages": "string" // Optional. Specify pages to process.
}
Responses
Success (200)
Returns the extracted text from the document.{
"text": "string" // Extracted text content
}
- X-RateLimit-Limit: The rate limit for the user.
- X-RateLimit-Remaining: The remaining number of requests for the user.
Bad Request (400)
Returned if the request is invalid or the file format is unsupported.{
"error": "Error message describing the issue"
}
Internal Server Error (500)
Returned if there’s an error during the document processing.{
"error": "Error processing document"
}
Example Request
curl -X POST https://app.dumplingai.com/api/v1/doc-to-text \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"inputMethod": "url",
"file": "https://example.com/sample.pdf"
}'
Example Response
{
"text": "This is the extracted text content from the document..."
}
Notes
- Supported file formats: PDF and DOCX.
- Maximum file size may be limited (refer to your plan details).
- If using the URL method, ensure the file is publicly accessible.
- This endpoint uses 20 credits per request.
- The file type is automatically detected based on the file content.
- The “pages” field allows you to specify which pages to process:
- Use comma-separated values or ranges (e.g., “1, 2-” or “1, 2, 3-7”).
- The first page index is 1.
- Use ”!” before a number for inverted page numbers (e.g., “!1” for the last page).
- If not specified, all pages will be processed by default.
- The input must be in string format.
Rate Limiting
Rate limit headers (X-RateLimit-Limit and X-RateLimit-Remaining) are included in the response to indicate the user’s current rate limit status.Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
Indicates whether binary content is supplied via URL or base64-encoded string.
Available options:
url, base64 Document URL or base64-encoded file content to convert to text.
Optional page ranges to extract (e.g., '1-3,5').
Optional identifier describing where the API request originated.
Available options:
API, WEB, MAKE_DOT_COM, ZAPIER, N8N, PLAYGROUND, DEFAULT_AUTOMATION, AGENT_PREVIEW, AGENT_LIVE, AUTOPILOT, STUDIO Response
Plain text representation returned.
Plain text extracted from the source document.