{ "openapi": "3.0.1", "info": { "title": "Language Detector: Detect Text Language in Bulk (API)", "description": "Language detector API: detect the language of texts, web pages and dataset fields in bulk. ISO 639-1 code and name, confidence, top 3 candidates, script, reliability flag and optional mixed-language detection by sentence.", "version": "0.1", "x-build-id": "SzKiaGg5qM491zeIx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/data-done-right~language-detector/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-data-done-right-language-detector", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/data-done-right~language-detector/runs": { "post": { "operationId": "runs-sync-data-done-right-language-detector", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/data-done-right~language-detector/run-sync": { "post": { "operationId": "run-sync-data-done-right-language-detector", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "texts": { "title": "Texts", "type": "array", "description": "Texts to detect, one per line. Each line is one result row. Example: Bonjour tout le monde, comment allez-vous aujourd'hui ?", "items": { "type": "string" } }, "urls": { "title": "Page URLs (optional)", "type": "array", "description": "Web pages whose main text should be analysed. The page html lang attribute is returned as a second signal. Public pages only, no logins. Example: https://en.wikipedia.org/wiki/Language.", "items": { "type": "string" } }, "datasetId": { "title": "Dataset with texts (optional)", "type": "string", "description": "Optional. Pick an Apify dataset (for example the output of a scraper) and the field below is analysed for every item. Example: a dataset ID such as aBcD1234eFgH5678i." }, "datasetField": { "title": "Dataset field", "type": "string", "description": "Field of each dataset item that holds the text (or a list of texts). Dotted paths work. Example: review.text or comments.0. Default: text.", "default": "text" }, "detectMixed": { "title": "Detect mixed languages", "type": "boolean", "description": "Also split each text into sentences and detect every sentence, so a text that switches language returns a list of languages with their share. Example: true for bilingual reviews or emails. Needs texts of at least 20 characters.", "default": false }, "restrictToLanguages": { "title": "Only choose between these languages", "type": "array", "description": "Optional. Limit the answer to these languages (2-letter ISO 639-1 codes, at least two). This makes short texts much more accurate when you know the likely languages. Example: en, fr, de. Leave empty for all 75 languages.", "items": { "type": "string" } }, "accuracy": { "title": "Accuracy", "enum": [ "high", "fast" ], "type": "string", "description": "High uses the full language models (best on short texts, needs more memory and about 10-20 s to start). Fast uses a lighter mode that is quicker but less accurate on short texts. Example: high.", "default": "high" }, "reliableThreshold": { "title": "Reliable confidence", "minimum": 0.1, "maximum": 0.99, "type": "number", "description": "A result is flagged isReliable when its confidence is at least this value (and the text is 20+ characters). Range 0.1 to 0.99. Example: 0.7.", "default": 0.7 }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum texts and pages to process in this run. Items beyond the limit are listed as skipped and not charged. Example: 1000.", "default": 1000 }, "maxCharsPerText": { "title": "Max characters analysed per text", "minimum": 100, "maximum": 200000, "type": "integer", "description": "Longer texts are cut to this length for detection (charCount still shows the full length). 2,000 to 5,000 characters is plenty for a reliable answer. Example: 20000.", "default": 20000 }, "concurrency": { "title": "Parallel page downloads", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many page URLs are downloaded at the same time. Example: 4.", "default": 4 }, "timeoutSecs": { "title": "Page timeout (seconds)", "minimum": 5, "maximum": 300, "type": "number", "description": "Give up on a page URL after this many seconds. Example: 30.", "default": 30 }, "proxyConfiguration": { "title": "Proxy (optional, for page URLs)", "type": "object", "description": "Only used for page URLs. Leave empty to download pages directly." } } }, "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 } } } } } } } } } }