{
"openapi": "3.0.1",
"info": {
"title": "Arabic Image OCR & Saudi Invoice QR Reader",
"description": "Fast Arabic + English OCR for screenshots, documents and images (normalised and raw text, lines with confidence, RTL order), plus exact fields from Saudi ZATCA e-invoice QR codes (signature not checked). For receipts and Arabic-Indic digits use Arabic Receipt Reader.",
"version": "0.1",
"x-build-id": "hkuaaFFaAvlP1pRJk"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/saif-tools~arabic-image-ocr/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-saif-tools-arabic-image-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/saif-tools~arabic-image-ocr/runs": {
"post": {
"operationId": "runs-sync-saif-tools-arabic-image-ocr",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/saif-tools~arabic-image-ocr/run-sync": {
"post": {
"operationId": "run-sync-saif-tools-arabic-image-ocr",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"mode": {
"title": "Mode",
"enum": [
"text",
"qr"
],
"type": "string",
"description": "text: plain-text OCR (fast, cheapest) for screenshots, documents and clean images. Weak on Arabic-Indic digits (٠-٩): for receipts, invoices and prices use the Arabic Receipt Reader actor.
qr: exact fields from a Saudi ZATCA e-invoice QR code only (no OCR). Images without a ZATCA QR are free.",
"default": "text"
},
"imageUrls": {
"title": "Image URLs",
"type": "array",
"description": "Public links to JPEG, PNG, WebP, GIF, BMP or TIFF images. Images over 4 megapixels are downscaled to 4 MP before OCR. Leave empty to try the bundled sample image (free).",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"keyValueStoreRecords": {
"title": "Key-value store records",
"type": "array",
"description": "Images already uploaded to an Apify key-value store. Write record-key for this run's default store, or store-name-or-id/record-key.",
"items": {
"type": "string"
}
},
"includeQrFields": {
"title": "Plain-text mode: also read Saudi e-invoice QR fields",
"type": "boolean",
"description": "Text mode only. Decodes a ZATCA QR if one is present. Adds one exact-qr-fields event per image where such a QR is found; images without one cost nothing extra.",
"default": false
},
"languages": {
"title": "Text mode: Tesseract languages",
"type": "string",
"description": "Text mode only. Installed: ara, eng. Use ara+eng for mixed images, eng for English only.",
"default": "ara+eng"
},
"pageLayout": {
"title": "Text mode: page layout",
"enum": [
"single-column",
"auto",
"block",
"sparse"
],
"type": "string",
"description": "How Tesseract splits the image into text blocks.",
"default": "single-column"
},
"upscale": {
"title": "Text mode: upscale small text",
"enum": [
"auto",
"off",
"2x",
"3x"
],
"type": "string",
"description": "Auto enlarges images whose text is too small for OCR.",
"default": "auto"
},
"deskew": {
"title": "Straighten tilted images",
"type": "boolean",
"description": "Detects and corrects rotation up to ±10°.",
"default": true
},
"threshold": {
"title": "Text mode: binarisation",
"enum": [
"none",
"otsu",
"adaptive"
],
"type": "string",
"description": "Converts the image to black and white before OCR. Try adaptive for photos with uneven lighting.",
"default": "none"
},
"digitSecondPass": {
"title": "Arabic-Indic digit second pass",
"type": "boolean",
"description": "Re-reads Arabic-Indic and Persian digits with a dedicated digit classifier.",
"default": true
},
"maskQrCodes": {
"title": "Hide QR codes from OCR",
"type": "boolean",
"description": "Blanks detected QR codes before OCR so they don't turn into junk text.",
"default": true
},
"stripTatweel": {
"title": "Remove tatweel (ـ) in the normalised text",
"type": "boolean",
"description": "The normalised fields drop tatweel and map Arabic-Indic and Persian digits to 0-9 (٫ → . and ٬ → ,). The raw fields keep the text as read.",
"default": true
},
"outputLines": {
"title": "Include lines with confidence",
"type": "boolean",
"description": "One entry per text line with its confidence, bounding box and direction.",
"default": true
},
"outputWords": {
"title": "Include word boxes",
"type": "boolean",
"description": "Adds the words of each line with their bounding boxes. Makes rows much larger.",
"default": false
},
"maxImageSizeMb": {
"title": "Maximum image size (MB)",
"minimum": 1,
"maximum": 100,
"type": "integer",
"description": "Larger files are skipped with a free error row.",
"default": 20
},
"maxConcurrency": {
"title": "Parallel images",
"minimum": 1,
"maximum": 8,
"type": "integer",
"description": "How many images are processed at the same time.",
"default": 2
}
}
},
"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
}
}
}
}
}
}
}
}
}
}