{ "openapi": "3.0.1", "info": { "title": "Image to Text OCR: 120+ Languages, Hebrew, Arabic, CJK", "description": "Extract text from images and scanned PDFs in 123 languages, including Hebrew, Arabic, Chinese, Japanese, Korean and Hindi. Lines with boxes and confidence, script auto-detect, rotated pages turned upright. Tesseract OCR, pay per page.", "version": "0.1", "x-build-id": "UUE9uGxYJoqDMpZMZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/itayozer9~image-ocr-multilang/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-itayozer9-image-ocr-multilang", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/itayozer9~image-ocr-multilang/runs": { "post": { "operationId": "runs-sync-itayozer9-image-ocr-multilang", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/itayozer9~image-ocr-multilang/run-sync": { "post": { "operationId": "run-sync-itayozer9-image-ocr-multilang", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "maxItems": 1000, "type": "array", "description": "Links to images (JPEG, PNG, WebP, TIFF, GIF, BMP) or scanned PDFs, one per line, up to 1,000 per run. The sample is a public test image from the Tesseract project: replace it with your own.", "items": { "type": "string" } }, "files": { "title": "Upload images or PDFs", "type": "array", "description": "Or upload files from your computer. They are stored in your own Apify key-value store." }, "languages": { "title": "Languages", "type": "array", "description": "Languages of the text. Pick every language that appears (each extra language makes reading slower). Auto detects the script of each page (Hebrew, Arabic, Cyrillic, Chinese, Devanagari and others) and turns rotated pages upright; for Latin-script text it reads English, so pick French, German, Spanish and so on yourself to get their accents.", "items": { "type": "string", "enum": [ "auto", "afr", "sqi", "amh", "ara", "hye", "asm", "aze", "aze_cyrl", "eus", "bel", "ben", "bos", "bre", "bul", "mya", "cat", "ceb", "chr", "chi_sim", "chi_sim_vert", "chi_tra", "chi_tra_vert", "cos", "hrv", "ces", "dan", "div", "nld", "dzo", "eng", "enm", "epo", "est", "fao", "fil", "fin", "fra", "frm", "fry", "glg", "kat", "kat_old", "deu", "frk", "ell", "grc", "guj", "hat", "heb", "hin", "hun", "isl", "ind", "iku", "gle", "ita", "ita_old", "jpn", "jpn_vert", "jav", "kan", "kaz", "khm", "kor", "kor_vert", "kmr", "kir", "lao", "lat", "lav", "lit", "ltz", "mkd", "msa", "mal", "mlt", "mri", "mar", "mon", "nep", "nor", "oci", "ori", "pus", "fas", "pol", "por", "pan", "que", "ron", "rus", "san", "gla", "srp", "srp_latn", "snd", "sin", "slk", "slv", "spa", "spa_old", "sun", "swa", "swe", "syr", "tgk", "tam", "tat", "tel", "tha", "bod", "tir", "ton", "tur", "ukr", "urd", "uig", "uzb", "uzb_cyrl", "vie", "cym", "yid", "yor" ], "enumTitles": [ "Auto: detect the script on each page (and turn rotated pages upright)", "Afrikaans (afr)", "Albanian (sqi)", "Amharic (amh)", "Arabic (ara)", "Armenian (hye)", "Assamese (asm)", "Azerbaijani (aze)", "Azerbaijani (Cyrillic) (aze_cyrl)", "Basque (eus)", "Belarusian (bel)", "Bengali (ben)", "Bosnian (bos)", "Breton (bre)", "Bulgarian (bul)", "Burmese (mya)", "Catalan (cat)", "Cebuano (ceb)", "Cherokee (chr)", "Chinese (Simplified) (chi_sim)", "Chinese (Simplified, vertical) (chi_sim_vert)", "Chinese (Traditional) (chi_tra)", "Chinese (Traditional, vertical) (chi_tra_vert)", "Corsican (cos)", "Croatian (hrv)", "Czech (ces)", "Danish (dan)", "Dhivehi (div)", "Dutch (nld)", "Dzongkha (dzo)", "English (eng)", "English (Middle English) (enm)", "Esperanto (epo)", "Estonian (est)", "Faroese (fao)", "Filipino (fil)", "Finnish (fin)", "French (fra)", "French (Middle French) (frm)", "Frisian (fry)", "Galician (glg)", "Georgian (kat)", "Georgian (Old) (kat_old)", "German (deu)", "German (Fraktur) (frk)", "Greek (ell)", "Greek (Ancient) (grc)", "Gujarati (guj)", "Haitian Creole (hat)", "Hebrew (heb)", "Hindi (hin)", "Hungarian (hun)", "Icelandic (isl)", "Indonesian (ind)", "Inuktitut (iku)", "Irish (gle)", "Italian (ita)", "Italian (Old) (ita_old)", "Japanese (jpn)", "Japanese (vertical) (jpn_vert)", "Javanese (jav)", "Kannada (kan)", "Kazakh (kaz)", "Khmer (khm)", "Korean (kor)", "Korean (vertical) (kor_vert)", "Kurdish (Kurmanji) (kmr)", "Kyrgyz (kir)", "Lao (lao)", "Latin (lat)", "Latvian (lav)", "Lithuanian (lit)", "Luxembourgish (ltz)", "Macedonian (mkd)", "Malay (msa)", "Malayalam (mal)", "Maltese (mlt)", "Maori (mri)", "Marathi (mar)", "Mongolian (mon)", "Nepali (nep)", "Norwegian (nor)", "Occitan (oci)", "Odia (ori)", "Pashto (pus)", "Persian (Farsi) (fas)", "Polish (pol)", "Portuguese (por)", "Punjabi (pan)", "Quechua (que)", "Romanian (ron)", "Russian (rus)", "Sanskrit (san)", "Scottish Gaelic (gla)", "Serbian (Cyrillic) (srp)", "Serbian (Latin) (srp_latn)", "Sindhi (snd)", "Sinhala (sin)", "Slovak (slk)", "Slovenian (slv)", "Spanish (spa)", "Spanish (Old) (spa_old)", "Sundanese (sun)", "Swahili (swa)", "Swedish (swe)", "Syriac (syr)", "Tajik (tgk)", "Tamil (tam)", "Tatar (tat)", "Telugu (tel)", "Thai (tha)", "Tibetan (bod)", "Tigrinya (tir)", "Tongan (ton)", "Turkish (tur)", "Ukrainian (ukr)", "Urdu (urd)", "Uyghur (uig)", "Uzbek (uzb)", "Uzbek (Cyrillic) (uzb_cyrl)", "Vietnamese (vie)", "Welsh (cym)", "Yiddish (yid)", "Yoruba (yor)" ] }, "default": [ "eng" ] }, "pages": { "title": "Pages", "maxLength": 200, "type": "string", "description": "For PDFs and multi-page TIFFs: which pages to read, for example 1-3, 7, 10- (page 10 to the end). Empty = all pages." }, "maxPagesPerFile": { "title": "Max pages per file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Pages after this many are skipped in each PDF or TIFF (1 to 2,000).", "default": 100 }, "boxes": { "title": "Boxes", "enum": [ "lines", "words", "none" ], "type": "string", "description": "Position of the text on the image, in pixels: per line, per line and per word, or none for smaller results.", "default": "lines" } } }, "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 } } } } } } } } } }