{ "openapi": "3.0.1", "info": { "title": "PDF & Image to Text: OCR for Scanned PDFs, Photos & Screenshots", "description": "Extract text from PDFs and images. Digital PDF pages are read exactly; scanned pages, photos and screenshots go through OCR in 16 languages. Paste a link, a Google Drive or Dropbox share link, or upload a file. Pay per page, from $1 per 1,000 pages.", "version": "0.1", "x-build-id": "TXR4c8m9dqSgKd6pQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/spokentext~pdf-image-to-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-spokentext-pdf-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/spokentext~pdf-image-to-text-ocr/runs": { "post": { "operationId": "runs-sync-spokentext-pdf-image-to-text-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/spokentext~pdf-image-to-text-ocr/run-sync": { "post": { "operationId": "run-sync-spokentext-pdf-image-to-text-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": { "urls": { "title": "PDF or image URLs", "type": "array", "description": "Direct links to PDF or image files (PNG, JPEG, TIFF, WEBP, BMP, GIF), or Google Drive and Dropbox share links. Share links must be open to anyone with the link.", "items": { "type": "string" } }, "file": { "title": "Or upload a file", "type": "string", "description": "Upload one PDF or image from your computer instead of pasting a link." }, "languages": { "title": "Languages for OCR", "type": "array", "description": "Languages printed in your scanned pages and images. Pick only the ones you need: each extra language makes OCR slower. Not used for digital PDF pages.", "items": { "type": "string", "enum": [ "en", "fr", "de", "es", "it", "pt", "nl", "pl", "sv", "da", "no", "fi", "cs", "tr", "ru", "uk" ], "enumTitles": [ "English", "French", "German", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Swedish", "Danish", "Norwegian", "Finnish", "Czech", "Turkish", "Russian", "Ukrainian" ] }, "default": [ "en" ] }, "ocrMode": { "title": "When to use OCR", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Digital PDF pages already contain their text, which is read exactly and costs less. OCR is needed for scans, photos and screenshots.", "default": "auto" }, "preserveLayout": { "title": "Keep the page layout", "type": "boolean", "description": "Keeps columns and tables aligned with spaces, as they appear on the page. Leave off for clean, flowing text. Applies to digital PDF pages.", "default": false }, "includePages": { "title": "Include text page by page", "type": "boolean", "description": "Adds a list with the text of each page and how it was read (text layer or OCR), besides the full text.", "default": true }, "maxPagesPerDocument": { "title": "Maximum pages per document", "minimum": 1, "type": "integer", "description": "Longer documents are cut at this many pages, so a single run can never cost more than you expect.", "default": 500 } } }, "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 } } } } } } } } } }