{ "openapi": "3.0.1", "info": { "title": "Image to Text OCR – 100+ Languages, Scanned PDFs, Word Boxes", "description": "Extract text from photos, scans, screenshots and scanned PDFs with Tesseract OCR in 100+ languages. Bulk URLs or uploads, confidence scores, auto-rotation, optional line and word bounding boxes.", "version": "1.0", "x-build-id": "bmgwdly3fzOM0wHEf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kris_fili~image-to-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kris_fili-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kris_fili~image-to-text-ocr/runs": { "post": { "operationId": "runs-sync-kris_fili-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kris_fili~image-to-text-ocr/run-sync": { "post": { "operationId": "run-sync-kris_fili-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Image or PDF URLs", "type": "array", "description": "Direct links to PNG, JPEG, TIFF (also multi-page), WebP, GIF, BMP images or scanned PDFs. Google Drive, Dropbox and GitHub share links are converted to downloads automatically.", "items": { "type": "string" } }, "files": { "title": "…or upload files", "type": "array", "description": "Upload images or PDFs from your computer (stored in your Apify key-value store)." }, "languages": { "title": "Languages", "type": "string", "description": "Language(s) of the text, joined with +, e.g. eng, deu, fra, spa, ita, por, pol, rus, ara, chi_sim, jpn, kor, eng+deu. Two-letter codes work too (en, de, fr). 100+ languages are supported – less common ones are downloaded automatically.", "default": "eng" }, "pageSegmentation": { "title": "Layout mode", "enum": [ "auto", "single-column", "single-block", "single-line", "sparse" ], "type": "string", "description": "Auto works for most images and documents. Single column suits receipts and narrow text, single line suits one-line crops and labels, sparse suits screenshots, forms, signs and memes with scattered text.", "default": "auto" }, "autoRotate": { "title": "Auto-rotate", "type": "boolean", "description": "Detect pages scanned sideways or upside down and rotate them before reading.", "default": true }, "includeLines": { "title": "Lines with bounding boxes", "type": "boolean", "description": "Add 'lines': every text line with its confidence and position (x, y, width, height in pixels of the original image).", "default": false }, "includeWordBoxes": { "title": "Words with bounding boxes", "type": "boolean", "description": "Add 'wordBoxes': every word with its confidence and position – for highlighting, redaction or reading form fields.", "default": false }, "pageRange": { "title": "Pages (PDF)", "type": "string", "description": "Read only these PDF pages, e.g. 1-3,5 (empty = all, up to the limit below)." }, "maxPagesPerFile": { "title": "Maximum pages per file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Limit for PDFs and multi-page TIFFs. Every page read is charged as one image.", "default": 50 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs." }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Bigger files are skipped with an error (no charge).", "default": 50 }, "maxConcurrency": { "title": "Files processed in parallel", "minimum": 1, "maximum": 16, "type": "integer", "description": "Empty = automatic (by the CPU cores of the run). More memory for the run = more cores = faster." } } }, "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 } } } } } } } } } }