Pricing

from $1.65 / 1,000 ocr pages

Try for free

Go to Apify Store

OCR API (Image to Text, Searchable PDF, 20 Languages)

Try for free

Extract text from images and scanned PDFs with OCR: plain text, Markdown, word boxes with confidence, or a searchable PDF. Each row has page, text, confidence, wordCount, rotation and method. Pages that already have text are read free. 20 languages, no API key. $3 per 1,000 OCR pages.

Pricing

from $1.65 / 1,000 ocr pages

Rating

0.0

(0)

Developer

locaihost data

Actor stats

Bookmarked

Total users

Monthly active users

7 days ago

Last modified

Categories

Developer tools

Automation

You can access the OCR API (Image to Text, Searchable PDF, 20 Languages) programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

{
  "openapi": "3.0.1",
  "info": {
    "version": "0.1",
    "x-build-id": "WrzAA1feZ96sHaDWW"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/locaihost~ocr/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-locaihost-ocr",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/locaihost~ocr/runs": {
      "post": {
        "operationId": "runs-sync-locaihost-ocr",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/locaihost~ocr/run-sync": {
      "post": {
        "operationId": "run-sync-locaihost-ocr",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "properties": {
          "startUrls": {
            "title": "Image or PDF URLs",
            "type": "array",
            "description": "Links to images (PNG, JPG, WebP, TIFF incl. multi-page, GIF, BMP, HEIC/HEIF, AVIF) or PDFs (scanned, mixed or born-digital). Public URLs or signed links (S3, GCS, Azure, Dropbox). Google Drive and Dropbox share links are turned into direct downloads. Up to 1,000 files per run.",
            "items": {
              "type": "object",
              "required": [
                "url"
              ],
              "properties": {
                "url": {
                  "type": "string",
                  "title": "URL of a web page",
                  "format": "uri"
                }
              }
            }
          },
          "uploadedFile": {
            "title": "Upload a file",
            "type": "string",
            "description": "Or upload one image or PDF from your computer."
          },
          "keyValueStore": {
            "title": "Key-value store with your files",
            "type": "string",
            "description": "OCR files already stored on Apify. Pick the store; the Actor gets read-only access to it for this run."
          },
          "keyValueStoreRecords": {
            "title": "Record keys",
            "type": "array",
            "description": "Keys of the files in the store above. Leave empty to OCR every record in the store.",
            "items": {
              "type": "string"
            }
          },
          "languages": {
            "title": "Languages",
            "type": "array",
            "description": "The languages on the page, up to 4. More languages make each page slower, so pick only what the documents use.",
            "items": {
              "type": "string",
              "enum": [
                "eng",
                "spa",
                "fra",
                "deu",
                "por",
                "ita",
                "nld",
                "pol",
                "rus",
                "ukr",
                "tur",
                "ara",
                "hin",
                "chi_sim",
                "chi_tra",
                "jpn",
                "kor",
                "vie",
                "ind",
                "tha"
              ],
              "enumTitles": [
                "English",
                "Spanish",
                "French",
                "German",
                "Portuguese",
                "Italian",
                "Dutch",
                "Polish",
                "Russian",
                "Ukrainian",
                "Turkish",
                "Arabic",
                "Hindi",
                "Chinese (Simplified)",
                "Chinese (Traditional)",
                "Japanese",
                "Korean",
                "Vietnamese",
                "Indonesian",
                "Thai"
              ]
            },
            "default": [
              "eng"
            ]
          },
          "outputMode": {
            "title": "Output",
            "enum": [
              "text",
              "markdown",
              "boxes"
            ],
            "type": "string",
            "description": "Every row has the page's plain text. Markdown adds a `markdown` field. Boxes adds `lines`, each with its words, pixel boxes [x0, y0, x1, y1] on the original page and a 0-100 confidence.",
            "default": "text"
          },
          "layout": {
            "title": "Page layout",
            "enum": [
              "auto",
              "block",
              "sparse"
            ],
            "type": "string",
            "description": "Auto runs full layout analysis (columns, paragraphs) and reads a narrow column such as a receipt line by line. Pick a fixed layout when you know what your images look like.",
            "default": "auto"
          },
          "searchablePdf": {
            "title": "Also make a searchable PDF",
            "type": "boolean",
            "description": "Saves one PDF per file with an invisible text layer over each OCR'd page, so you can search and copy text. Pages that already had text are kept as they were. The link is in each row (`searchablePdfUrl`) and the file is in the run's key-value store.",
            "default": false
          },
          "ocrMode": {
            "title": "Which PDF pages to OCR",
            "enum": [
              "auto",
              "always"
            ],
            "type": "string",
            "description": "Auto reads pages that already have selectable text straight from the PDF, exactly and for free, and OCRs scanned pages. Every page re-reads all pages with OCR (each one is charged), for PDFs whose text layer is broken or garbled.",
            "default": "auto"
          },
          "autoRotate": {
            "title": "Turn sideways and upside-down pages",
            "type": "boolean",
            "description": "Detects pages scanned or photographed at 90, 180 or 270 degrees and turns them upright.",
            "default": true
          },
          "deskew": {
            "title": "Straighten tilted pages",
            "type": "boolean",
            "description": "Levels pages scanned at a slight angle (up to 15 degrees).",
            "default": true
          },
          "enhance": {
            "title": "Fix lighting and faded print",
            "type": "boolean",
            "description": "Evens out shadows on phone photos, darkens faded or low-contrast print, and gives hard pages a second pass. Clean scans are left as they are.",
            "default": true
          },
          "maxPagesPerDocument": {
            "title": "Max pages per file",
            "minimum": 0,
            "maximum": 5000,
            "type": "integer",
            "description": "Only the first N pages of each PDF or TIFF. 0 = all pages.",
            "default": 0
          },
          "maxPages": {
            "title": "Max OCR pages per run",
            "minimum": 0,
            "maximum": 100000,
            "type": "integer",
            "description": "Stop after this many charged pages in the whole run. 0 = no limit (your maximum cost per run still applies).",
            "default": 0
          },
          "pdfDpi": {
            "title": "PDF render resolution",
            "minimum": 150,
            "maximum": 400,
            "type": "integer",
            "description": "Resolution scanned PDF pages are rendered at before OCR. 300 suits most documents; 400 can help very small print.",
            "default": 300
          },
          "maxFileSizeMb": {
            "title": "Max file size",
            "minimum": 1,
            "maximum": 500,
            "type": "integer",
            "description": "Larger files are skipped with a message (not charged).",
            "default": 100
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

OCR API: Image to Text and Scanned PDF to Text OpenAPI definition

OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.

OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.

By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.

You can download the OpenAPI definitions for OCR API (Image to Text, Searchable PDF, 20 Languages) from the options below:

OpenAPI.json

If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.

You can also check out our other API clients:

OCR API (Image to Text, Searchable PDF, 20 Languages) API in Python

OCR API (Image to Text, Searchable PDF, 20 Languages) API in JavaScript

OCR API (Image to Text, Searchable PDF, 20 Languages) API through CLI

OCR API (Image to Text, Searchable PDF, 20 Languages) API

Google Lens OCR API - Image to Text & Coordinates

thodor/google-lens-ocr

Google Lens OCR API. Extract text from images with word, line and paragraph bounding boxes in pixels, plus object detection and translation.

Thodor

OCR Text Extractor - Images & Scanned PDFs to Text

scrapesage/ocr-text-extractor

Extract text from images (PNG, JPG, TIFF, WEBP, BMP, GIF) and scanned PDFs with Tesseract OCR in 28 languages. Per-page text, confidence scores, optional word boxes, automatic text-layer detection for born-digital PDFs. No API key, no browser. JSON, CSV, Excel.

Scrape Sage

Image OCR Scraper

seemuapps/image-ocr-scraper

Extract text from any image. Bulk OCR for screenshots, scanned documents, receipts, signs, and photos. Supports 109 languages and outputs clean Markdown or structured JSON with bounding boxes.

Seemu Scraping

PDF OCR API - Document Extraction

alizarin_refrigerator-owner/pdf-ocr-api

Extract text from PDFs including scanned documents. OCR processing, table extraction & structured data output. Process invoices, contracts & forms at scale.

The Howlers

PDF Extractor 2.0

jupri/pdf-extractor-2-0

💫 Extract PDF Document Contents including Metadata, Images, Pages, Tables, Attachments, etc.

cat

173

Bulk Pdf To Json OCR

gagandeo/bulk-pdf-to-json-ocr

Convert PDF invoices, menus, images with text and documents into structured JSON. Features hybrid Digital+OCR parsing and AI-powered data extraction.

Kumar Gagandeo

PDF Text Extractor — Text, Markdown, Tables and OCR

lergassy/pdf-text-extractor

[$0.003/PDF] Extract text from PDF files by URL, upload or base64: full text, per-page text, Markdown, tables and metadata. Scanned pages are read with OCR in 19 languages. Password PDFs, page ranges, RAG chunks. No fee per run.

Matvey

Pdf To Jpg Converter

programmersoham/pdf-to-jpg-converter

Convert PDF documents into high-quality JPEG images. Supports batch processing, customizable resolution (72-300 DPI), page ranges, and flexible output (URLs, ZIP, or both). Perfect for web developers, content creators, e-commerce, education, and marketing teams.

Soham Purohit

Speech to Text — Audio Transcription API, 100+ Languages

vivid_astronaut/speech-to-text

Transcribe audio to text with high accuracy in 100+ languages, with speaker detection and word timestamps. Input an audio file, get structured transcript JSON — ready for subtitles, meeting notes, and voice apps.

BRAINIALL Team

Website Screenshot API (Full Page, Mobile, PDF)

locaihost/screenshot

Capture screenshots or PDFs of up to 5,000 web pages or your own HTML per run. Each row gives a public image link, final URL, HTTP status, title, file size and the cookie banner it closed. Full page, one element, 11 device presets, dark mode. Failed pages free. $0.89 per 1,000 screenshots.