{ "openapi": "3.0.1", "info": { "title": "Image to Text OCR - Extract Text from Images & Scanned PDFs", "description": "Extract text from images and scanned PDFs in bulk with Tesseract OCR: screenshots, documents, receipts, posters. 12 languages, text with paragraphs, word count, confidence and optional line boxes. URLs, scanned PDF pages or another Actor's dataset. No external AI API.", "version": "1.0", "x-build-id": "TZtTrIHBajm64PRcX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/teddythebuilder~image-to-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-teddythebuilder-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/teddythebuilder~image-to-text-ocr/runs": { "post": { "operationId": "runs-sync-teddythebuilder-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/teddythebuilder~image-to-text-ocr/run-sync": { "post": { "operationId": "run-sync-teddythebuilder-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "imageUrls": { "title": "Image URLs", "type": "array", "description": "Images to read: PNG, JPG, WebP, GIF, BMP, TIFF. One URL per line.", "default": [ "https://tesseract-ocr.github.io/tessdoc/images/eurotext.png" ], "items": { "type": "string" } }, "pdfUrls": { "title": "Scanned PDF URLs", "type": "array", "description": "Scanned PDFs (or any PDF): each page is rendered and OCR'd. For PDFs that already contain selectable text, the PDF Text Extractor is cheaper.", "default": [], "items": { "type": "string" } }, "datasetId": { "title": "Dataset ID with image URLs", "type": "string", "description": "Read image/PDF URLs from another Apify dataset, e.g. the output of an image scraper or the Bulk Image & File Downloader (field fileUrl)." }, "datasetUrlField": { "title": "URL field", "type": "string", "description": "Field in the dataset items that holds the URL (or a list of URLs), e.g. imageUrl, fileUrl, url.", "default": "url" }, "languages": { "title": "Languages", "type": "array", "description": "Languages in the images. Pick all that occur; more languages are slower. English is the default.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "swe", "nor", "dan", "fin", "pol" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Swedish", "Norwegian", "Danish", "Finnish", "Polish" ] }, "default": [ "eng" ] }, "layout": { "title": "Page layout", "enum": [ "auto", "sparse", "single-block", "single-line" ], "type": "string", "description": "Auto works for documents and screenshots. Sparse finds scattered text (posters, product photos, memes). Single block for one paragraph, single line for banners and captions.", "default": "auto" }, "minWordConfidence": { "title": "Min word confidence (0-100)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Drop words Tesseract is less sure about, e.g. 40 to remove noise from photos. 0 = keep all words.", "default": 0 }, "includeLines": { "title": "Include lines with boxes", "type": "boolean", "description": "Also return every text line with its confidence and bounding box [x, y, width, height] in original image pixels.", "default": false }, "maxItems": { "title": "Max images / PDF pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many images and PDF pages. You pay per image or page processed.", "default": 100 }, "maxPdfPages": { "title": "Max pages per PDF", "minimum": 0, "type": "integer", "description": "OCR at most this many pages of each PDF (from the start). 0 = all pages.", "default": 20 }, "pdfDpi": { "title": "PDF render resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "200 is a good balance; use 300 for small print.", "default": 200 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Skip larger files (free).", "default": 30 }, "maxConcurrency": { "title": "Parallel OCR workers", "minimum": 1, "maximum": 8, "type": "integer", "description": "Images processed at the same time. Defaults to the number of CPU cores of the run (raise memory for more cores)." } } }, "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 } } } } } } } } } }