{ "openapi": "3.0.1", "info": { "title": "OCR — Scanned PDF & Image to Text (Tesseract, 29 Languages)", "description": "Extract text from scanned PDFs and images (PNG, JPEG, TIFF, WebP, GIF, BMP) with Tesseract 5 OCR in 29 languages. PDF pages that already have text are read directly at a tenth of the price. Per-page text and confidence, optional word bounding boxes. $3 per 1,000 OCR pages.", "version": "0.1", "x-build-id": "bP14abUHpShCo3mHx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/actor-forge~ocr-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-actor-forge-ocr-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/actor-forge~ocr-to-text/runs": { "post": { "operationId": "runs-sync-actor-forge-ocr-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/actor-forge~ocr-to-text/run-sync": { "post": { "operationId": "run-sync-actor-forge-ocr-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", "required": [ "urls" ], "properties": { "urls": { "title": "Image or PDF URLs", "type": "array", "description": "Links to scanned PDFs or images (PNG, JPEG, TIFF, WebP, GIF, BMP, JPEG 2000). Each image is one page.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "Languages in the documents (up to 4). Picking only the languages you need is faster and more accurate.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "swe", "dan", "nor", "fin", "ces", "hun", "ron", "tur", "rus", "ukr", "slk", "ara", "heb", "hin", "chi_sim", "chi_tra", "jpn", "kor", "vie", "ind", "tha" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Swedish", "Danish", "Norwegian", "Finnish", "Czech", "Hungarian", "Romanian", "Turkish", "Russian", "Ukrainian", "Slovak", "Arabic", "Hebrew", "Hindi", "Chinese (Simplified)", "Chinese (Traditional)", "Japanese", "Korean", "Vietnamese", "Indonesian", "Thai" ] }, "default": [ "eng" ] }, "pdfMode": { "title": "PDF pages with text", "enum": [ "auto", "ocr-all" ], "type": "string", "description": "Auto: pages that already contain text are read directly (exact, and charged at the cheaper text-layer price); only scanned pages are OCR'd. OCR all: OCR every page, e.g. when a PDF's hidden text layer is poor.", "default": "auto" }, "outputMode": { "title": "Output rows", "enum": [ "document", "pages" ], "type": "string", "description": "For PDFs: one row per PDF with all pages, or one row per page. Images are always one row each.", "default": "document" }, "includeWords": { "title": "Include word bounding boxes", "type": "boolean", "description": "Add every recognised word with its confidence and pixel box (left, top, width, height), e.g. for redaction, highlighting or form extraction.", "default": false }, "minWordConfidence": { "title": "Minimum word confidence", "minimum": 0, "maximum": 100, "type": "integer", "description": "Drop words Tesseract is less sure of than this (0–100). 0 keeps everything; 40–60 removes most noise from stains and stamps.", "default": 0 }, "pageSegmentation": { "title": "Page layout", "enum": [ "auto", "single-column", "single-block", "sparse" ], "type": "string", "description": "How Tesseract finds text. Auto suits most pages; Single column for uniform text; Single block for receipts and snippets; Sparse for scattered text like forms and screenshots.", "default": "auto" }, "dpi": { "title": "PDF render resolution (DPI)", "minimum": 100, "maximum": 600, "type": "integer", "description": "Resolution scanned PDF pages are rendered at before OCR. 300 is the accuracy sweet spot; 200 is faster for large print.", "default": 300 }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Process at most this many pages of each PDF (from the start). Longer PDFs are marked truncated.", "default": 200 }, "maxFiles": { "title": "Max files", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop after this many files.", "default": 1000 }, "password": { "title": "PDF password", "type": "string", "description": "For password-protected PDFs you are entitled to open. Used for every PDF in the run." } } }, "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 } } } } } } } } } }