Image to Text API
Pricing
from $1.60 / 1,000 image reads
Go to Apify Store
Image to Text API
Image to text: OCR with line and word positions and confidence scores. $0.002 per image OCR result; start extra; usage included; failed results uncharged.
Image to Text API
Pricing
from $1.60 / 1,000 image reads
Image to text: OCR with line and word positions and confidence scores. $0.002 per image OCR result; start extra; usage included; failed results uncharged.
You can access the Image to Text API programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "Ncg5P24cBeFX8Xh1W" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hermeskd~image-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hermeskd-image-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/hermeskd~image-to-text/runs": { "post": { "operationId": "runs-sync-hermeskd-image-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/hermeskd~image-to-text/run-sync": { "post": { "operationId": "run-sync-hermeskd-image-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "urls" ], "properties": { "urls": { "title": "Image URLs", "minItems": 1, "maxItems": 1000, "type": "array", "description": "Image URLs (PNG, JPEG, WebP, TIFF, BMP, GIF), http or https, 1–1,000 per run, up to 20 MB, 50 megapixels and 32,767 pixels on a side each. Each URL becomes one record. Processing is sequential, with 540 seconds of work inside the default 600-second run at 1,024 MB; unfinished URLs receive timeout records.", "items": { "type": "string", "pattern": "^https?://[^\\s/@]+([/?#]\\S*)?$" } }, "languages": { "title": "Languages", "minItems": 1, "maxItems": 3, "type": "array", "description": "Explicit Tesseract language/variant codes; 1–3 per image, 123 available codes covering 100+ languages. Unknown codes fail validation, never silently English.", "items": { "type": "string", "enum": [ "afr", "amh", "ara", "asm", "aze", "aze_cyrl", "bel", "ben", "bod", "bos", "bre", "bul", "cat", "ceb", "ces", "chi_sim", "chi_sim_vert", "chi_tra", "chi_tra_vert", "chr", "cos", "cym", "dan", "deu", "deu_latf", "div", "dzo", "ell", "eng", "enm", "epo", "est", "eus", "fao", "fas", "fil", "fin", "fra", "frm", "fry", "gla", "gle", "glg", "grc", "guj", "hat", "heb", "hin", "hrv", "hun", "hye", "iku", "ind", "isl", "ita", "ita_old", "jav", "jpn", "jpn_vert", "kan", "kat", "kat_old", "kaz", "khm", "kir", "kmr", "kor", "kor_vert", "lao", "lat", "lav", "lit", "ltz", "mal", "mar", "mkd", "mlt", "mon", "mri", "msa", "mya", "nep", "nld", "nor", "oci", "ori", "pan", "pol", "por", "pus", "que", "ron", "rus", "san", "sin", "slk", "slv", "snd", "spa", "spa_old", "sqi", "srp", "srp_latn", "sun", "swa", "swe", "syr", "tam", "tat", "tel", "tgk", "tha", "tir", "ton", "tur", "uig", "ukr", "urd", "uzb", "uzb_cyrl", "vie", "yid", "yor" ], "enumTitles": [ "afr", "amh", "ara", "asm", "aze", "aze_cyrl", "bel", "ben", "bod", "bos", "bre", "bul", "cat", "ceb", "ces", "chi_sim", "chi_sim_vert", "chi_tra", "chi_tra_vert", "chr", "cos", "cym", "dan", "deu", "deu_latf", "div", "dzo", "ell", "eng", "enm", "epo", "est", "eus", "fao", "fas", "fil", "fin", "fra", "frm", "fry", "gla", "gle", "glg", "grc", "guj", "hat", "heb", "hin", "hrv", "hun", "hye", "iku", "ind", "isl", "ita", "ita_old", "jav", "jpn", "jpn_vert", "kan", "kat", "kat_old", "kaz", "khm", "kir", "kmr", "kor", "kor_vert", "lao", "lat", "lav", "lit", "ltz", "mal", "mar", "mkd", "mlt", "mon", "mri", "msa", "mya", "nep", "nld", "nor", "oci", "ori", "pan", "pol", "por", "pus", "que", "ron", "rus", "san", "sin", "slk", "slv", "snd", "spa", "spa_old", "sqi", "srp", "srp_latn", "sun", "swa", "swe", "syr", "tam", "tat", "tel", "tgk", "tha", "tir", "ton", "tur", "uig", "ukr", "urd", "uzb", "uzb_cyrl", "vie", "yid", "yor" ] }, "default": [ "eng" ] }, "granularity": { "title": "Granularity", "enum": [ "text", "lines", "words", "paragraphs" ], "type": "string", "description": "text returns plain text only; lines adds each line with its confidence and box; words adds each word with its confidence and box. paragraphs adds each paragraph with confidence and a box.", "default": "lines" }, "minConfidence": { "title": "Minimum confidence", "minimum": 0, "maximum": 100, "type": "integer", "description": "Drop words read with a confidence below this (0–100), and lines left with no word; 0 keeps everything.", "default": 0 }, "layout": { "title": "Text layout", "enum": [ "auto", "single_block", "single_line", "single_word", "sparse_text", "raw_line" ], "type": "string", "description": "Tesseract layout: auto (PSM 3), single_block (6), single_line (7), single_word (8), sparse_text (11), raw_line (13). No automatic detection of selected language.", "default": "auto" }, "threshold": { "title": "Threshold image", "type": "boolean", "description": "Use a fixed 128 grayscale threshold before OCR; off preserves the existing grayscale and resize path.", "default": false }, "normalizeBoxes": { "title": "Normalized boxes", "type": "boolean", "description": "Add boxNorm with x,y,w,h in 0–1 image coordinates beside each pixel box.", "default": false }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Add escaped Markdown text, preserving source lines and paragraphs without inventing headings.", "default": false }, "includeConfidence": { "title": "Include mean confidence", "type": "boolean", "description": "Add mean confidence of kept words (0–100), or null for no kept words.", "default": false } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Image to Text API from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: