{ "openapi": "3.0.1", "info": { "title": "Image to Text OCR - Photos, Screenshots & Scanned PDFs", "description": "Extract text from images, screenshots, photos and scanned PDFs with a local open-source OCR engine (PP-OCR). Line-level bounding boxes, confidence scores and clean reading-order text. No Google, no API key. Pay only per page read.", "version": "1.0", "x-build-id": "fep4SiWJaOLmfn1hV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kantolabs~image-to-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kantolabs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kantolabs~image-to-text-ocr/runs": { "post": { "operationId": "runs-sync-kantolabs-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kantolabs~image-to-text-ocr/run-sync": { "post": { "operationId": "run-sync-kantolabs-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "sources" ], "properties": { "sources": { "title": "Image or PDF URLs", "type": "array", "description": "Direct links to images (PNG, JPG, WEBP, TIFF, BMP, GIF, HEIC) or PDF files, one per line. Scanned PDFs are OCR'd page by page. Files stored in an Apify key-value store or any public bucket work too.", "default": [ "https://raw.githubusercontent.com/tesseract-ocr/tessdoc/main/images/eurotext.png", "https://raw.githubusercontent.com/RapidAI/RapidOCR/main/python/tests/test_files/ch_en_num.jpg", "https://raw.githubusercontent.com/ocrmypdf/OCRmyPDF/main/tests/resources/skew.pdf" ], "items": { "type": "string" } }, "quality": { "title": "OCR model", "enum": [ "fast", "accurate" ], "type": "string", "description": "`fast` (PP-OCRv6 tiny) is excellent for screenshots, documents and Latin-script text and costs $3 per 1,000 pages. `accurate` (PP-OCRv6 small) is about 4x slower and better on dense Chinese/Japanese text, stylized fonts and poor photos; it is billed as a separate, higher-priced event.", "default": "fast" }, "includeLines": { "title": "Include text lines with bounding boxes", "type": "boolean", "description": "Add a `lines` array: each detected text line with its confidence and pixel box [x0, y0, x1, y1]. Turn off for plain text only.", "default": true }, "minConfidence": { "title": "Minimum confidence (0-1)", "enum": [ "0.3", "0.4", "0.5", "0.6", "0.7", "0.8" ], "type": "string", "description": "Drop text lines recognized with lower confidence than this. 0.5 removes most noise; lower it for very poor scans.", "default": "0.5" }, "pdfMode": { "title": "PDF mode", "enum": [ "auto", "ocr" ], "type": "string", "description": "`auto` uses a PDF page's own text layer when it has one (exact, fast) and runs OCR only on scanned pages. `ocr` always runs OCR on every page.", "default": "auto" }, "maxPdfPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 500, "type": "integer", "description": "Only the first N pages of each PDF are read (each page is billed as one result).", "default": 50 }, "pdfDpi": { "title": "PDF render resolution (DPI)", "minimum": 72, "maximum": 400, "type": "integer", "description": "Resolution used to rasterize scanned PDF pages before OCR. 200 is right for normal documents; use 300 for small print.", "default": 200 }, "skipEmpty": { "title": "Do not bill pages with no text", "type": "boolean", "description": "When an image or page contains no readable text it is reported with an error message and not charged.", "default": true }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped (free).", "default": 50 }, "requestTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Give up on a file that does not download within this time.", "default": 60 } } }, "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 } } } } } } } } } }