PDF to Text Extractor with OCR: PDF, DOCX & Images
Pricing
from $2.50 / 1,000 document converteds
Extract text from PDF, Word (DOCX) and image files by URL; scanned pages are read with OCR (7 languages). Use to turn documents into text for search or LLMs; optional tables to CSV/JSON. Input: fileUrls. Output per file: status, text, per-page text, page count, OCR pages, metadata, tables.
You can access the PDF to Text Extractor with OCR: PDF, DOCX & Images programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "kQcSrKcADp4WPX9ch" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/phaux~pdf-docx-ocr-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-phaux-pdf-docx-ocr-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/phaux~pdf-docx-ocr-text-extractor/runs": { "post": { "operationId": "runs-sync-phaux-pdf-docx-ocr-text-extractor", "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/phaux~pdf-docx-ocr-text-extractor/run-sync": { "post": { "operationId": "run-sync-phaux-pdf-docx-ocr-text-extractor", "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": { "fileUrls": { "title": "File URLs", "type": "array", "description": "Public http(s) links to PDF, DOCX or image files (PNG, JPEG, TIFF, GIF, BMP, WEBP). Each URL is checked against its site's robots.txt and must resolve to a public IP. Leave empty and add no key-value store files to run the small example PDF.", "items": { "type": "string" } }, "keyValueStore": { "title": "Key-value store with your files", "type": "string", "description": "Optional. Pick (or give the ID or name of) a key-value store you uploaded files to. The Actor gets read-only access to this store only. Each record's content must be the raw file. Example: \"my-documents\" (a store name or ID in your account)." }, "keyValueStoreKeys": { "title": "Record keys", "type": "array", "description": "Record keys of the files in that store, e.g. 'scan.pdf'. Leave empty to process every record in the store (up to 1,000).", "items": { "type": "string" } }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto OCRs a PDF page only when its text layer has fewer than 'Min text characters per page'. Images are always OCR'd unless Never. Default: \"auto\".", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Tesseract language codes joined with '+', e.g. 'eng' or 'eng+deu'. Installed: eng, deu, fra, spa, por, ita, nld. Default: \"eng\".", "default": "eng" }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Resolution scanned PDF pages are rendered at before OCR. 300 is Tesseract's sweet spot; lower is faster but less accurate. Default: 300.", "default": 300 }, "minTextCharsPerPage": { "title": "Min text characters per page (auto OCR)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "In auto mode, a PDF page whose text layer has fewer letters/digits than this is OCR'd. Default: 25.", "default": 25 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are refused before download (not charged). Default: 50.", "default": 50 }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Only the first N pages are extracted; the item is marked truncated. Default: 200.", "default": 200 }, "maxOcrPagesPerDocument": { "title": "Max OCR pages per document", "minimum": 0, "maximum": 500, "type": "integer", "description": "Caps OCR work (and OCR charges) per document. Extra scanned pages are left empty and listed in warnings. Default: 50.", "default": 50 }, "includePageTexts": { "title": "Include per-page texts", "type": "boolean", "description": "Add the 'pages' array (text per page). The full text is always in 'text'. Default: true.", "default": true }, "extractTables": { "title": "Extract tables to CSV / JSON", "type": "boolean", "description": "Off by default. When on, tables in PDF text layers (pdfplumber) and DOCX files are also returned: each table as JSON rows in the item's 'tables' field plus a CSV file in the key-value store (csvUrl). Scanned/OCR pages and images are skipped. No extra charge: the document price is the same.", "default": false }, "tableStrategy": { "title": "Table detection", "enum": [ "lines", "text" ], "type": "string", "description": "PDF only. 'lines' finds tables drawn with borders or rules. 'text' guesses columns from text alignment for borderless tables; check the result. Default: \"lines\".", "default": "lines" }, "maxConcurrency": { "title": "Documents in parallel", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many documents are downloaded and processed at once. OCR inside a document uses all CPU cores (~1 core per 4 GB memory). Default: 2.", "default": 2 }, "timeBudgetSecs": { "title": "Time budget (seconds)", "minimum": 0, "maximum": 86400, "type": "integer", "description": "Stop starting new work after this many seconds and finish SUCCEEDED with what is done. 0 = automatic (run timeout minus a safety margin). Default: 0.", "default": 0 } } }, "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 } } } } } } } } }}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 PDF to Text Extractor with OCR: PDF, DOCX & Images from the options below:
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: