{ "openapi": "3.0.1", "info": { "title": "OCR: Image & Scanned PDF to Text (Tesseract, 40 languages)", "description": "Bulk OCR for images and scanned PDFs: image to text and scanned PDF to text in 40 languages with Tesseract 5. Per-page text, confidence score, optional word bounding boxes and hOCR. Auto-rotation, smart PDF text-layer mode. Blank pages and errors are free.", "version": "0.1", "x-build-id": "lzz4XVJuCIfeJXjlH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/timeout~ocr-image-pdf-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-timeout-ocr-image-pdf-to-text", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/timeout~ocr-image-pdf-to-text/runs": { "post": { "operationId": "runs-sync-timeout-ocr-image-pdf-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/timeout~ocr-image-pdf-to-text/run-sync": { "post": { "operationId": "run-sync-timeout-ocr-image-pdf-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sources": { "title": "Image or PDF URLs", "type": "array", "description": "Public http(s) links to images (PNG, JPEG, TIFF incl. multi-page, WEBP, GIF, BMP) or PDFs (scanned or digital). One dataset item is returned per page.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "languages": { "title": "Languages", "type": "array", "description": "Languages of the text. Put the main language first; pick only the languages that actually appear (each extra language makes OCR slower and can lower accuracy).", "items": { "type": "string", "enum": [ "eng", "spa", "deu", "fra", "ita", "por", "nld", "pol", "ces", "slk", "ron", "hun", "tur", "swe", "dan", "nor", "fin", "cat", "glg", "eus", "ell", "rus", "ukr", "bul", "hrv", "srp_latn", "slv", "lit", "lav", "est", "ara", "heb", "hin", "vie", "ind", "tha", "chi_sim", "chi_tra", "jpn", "kor" ], "enumTitles": [ "English", "Spanish", "German", "French", "Italian", "Portuguese", "Dutch", "Polish", "Czech", "Slovak", "Romanian", "Hungarian", "Turkish", "Swedish", "Danish", "Norwegian", "Finnish", "Catalan", "Galician", "Basque", "Greek", "Russian", "Ukrainian", "Bulgarian", "Croatian", "Serbian (Latin)", "Slovenian", "Lithuanian", "Latvian", "Estonian", "Arabic", "Hebrew", "Hindi", "Vietnamese", "Indonesian", "Thai", "Chinese (Simplified)", "Chinese (Traditional)", "Japanese", "Korean" ] }, "default": [ "eng" ] }, "pdfMode": { "title": "PDF mode", "enum": [ "auto", "ocr" ], "type": "string", "description": "auto: pages that already have a text layer are extracted directly (cheaper, exact), other pages are OCR'd. ocr: always render and OCR every page.", "default": "auto" }, "includeWords": { "title": "Include words with bounding boxes", "type": "boolean", "description": "Add words[] with text, confidence (0-100), bbox [x0,y0,x1,y1] in pixels of the OCR'd image, block and line number.", "default": false }, "includeHocr": { "title": "Include hOCR", "type": "boolean", "description": "Add the hOCR (HTML with layout and coordinates) of each OCR'd page.", "default": false }, "autoRotate": { "title": "Auto-rotate pages", "type": "boolean", "description": "Detect pages scanned sideways or upside down (90/180/270 degrees) and rotate them before OCR.", "default": true }, "upscaleSmallImages": { "title": "Upscale small images", "type": "boolean", "description": "Images under 1000 px are enlarged before OCR (improves small text such as screenshots and thumbnails).", "default": true }, "pageSegmentation": { "title": "Page layout", "enum": [ "auto", "single-column", "single-block", "sparse-text", "single-line" ], "type": "string", "description": "How Tesseract splits the page. 'auto' fits documents; 'sparse-text' fits photos, receipts and screenshots with scattered text; 'single-line' fits one-line crops.", "default": "auto" }, "pdfDpi": { "title": "PDF render resolution (DPI)", "minimum": 100, "maximum": 600, "type": "integer", "description": "Resolution used to render scanned PDF pages for OCR. 300 is the standard; use 400 for very small print.", "default": 300 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs (applied to all PDFs in the run)." }, "keyValueStoreKeys": { "title": "Key-value store keys (optional)", "type": "array", "description": "Process files stored as records in an Apify key-value store (for example saved by another Actor or via the API) instead of, or in addition to, URLs.", "items": { "type": "string" } }, "keyValueStoreId": { "title": "Key-value store ID or name (optional)", "type": "string", "description": "Key-value store that holds the keys above (pick it, or paste its ID). Empty = this run's default key-value store." }, "maxFiles": { "title": "Max files", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Safety cap on the number of files processed in one run.", "default": 100 }, "maxPagesPerFile": { "title": "Max pages per file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Only the first N pages of each PDF / multi-page TIFF are processed.", "default": 50 }, "maxTotalPages": { "title": "Max pages per run", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Safety cap on the total pages (and therefore cost) of one run.", "default": 500 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped with an error item (not charged).", "default": 25 } } }, "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 } } } } } } } } } }