Tatoeba Sentence Corpus Scraper
Pricing
from $10.00 / 1,000 result items
Scrapes Tatoeba sentences and translations by language pair, search term, or tag. Returns each sentence as a flat row with metadata.
You can access the Tatoeba Sentence Corpus Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, youโll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "E99WxEhjGytEgqOd3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~tatoeba-sentence-corpus-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-tatoeba-sentence-corpus-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/parseforge~tatoeba-sentence-corpus-scraper/runs": { "post": { "operationId": "runs-sync-parseforge-tatoeba-sentence-corpus-scraper", "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/parseforge~tatoeba-sentence-corpus-scraper/run-sync": { "post": { "operationId": "run-sync-parseforge-tatoeba-sentence-corpus-scraper", "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": { "maxItems": { "title": "Maximum sentences", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "How many sentences to collect per run." }, "query": { "title": "Search term for sentences", "type": "string", "description": "Text to search for in sentences. Leave empty to browse a language without a filter." }, "fromLanguage": { "title": "From Language", "enum": [ "eng", "spa", "fra", "deu", "ita", "por", "rus", "cmn", "jpn", "ara", "nld", "tur", "kor", "pol", "ukr", "ron", "ell", "heb", "ces", "hin", "tha", "vie", "ind", "msa", "ben", "fin", "swe", "nor", "dan", "hun", "fil", "yue", "cat", "epo", "lat", "fas", "urd", "tam", "tel", "mar", "isl", "slk", "srp", "hrv", "bul", "slv", "est", "lit", "lav", "afr" ], "type": "string", "description": "Source language (ISO 639-3 code) for the sentences themselves." }, "toLanguage": { "title": "To Language", "enum": [ "eng", "spa", "fra", "deu", "ita", "por", "rus", "cmn", "jpn", "ara", "nld", "tur", "kor", "pol", "ukr", "ron", "ell", "heb", "ces", "hin", "tha", "vie", "ind", "msa", "ben", "fin", "swe", "nor", "dan", "hun", "fil", "yue", "cat", "epo", "lat", "fas", "urd", "tam", "tel", "mar", "isl", "slk", "srp", "hrv", "bul", "slv", "est", "lit", "lav" ], "type": "string", "description": "Target translation language (ISO 639-3 code). Leave empty for all available translations." }, "tags": { "title": "Tags", "type": "array", "description": "Filter sentences by Tatoeba tag names (e.g. proverb, idiom, greeting).", "items": { "type": "string" } } } }, "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 } } }, "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 } } } } } } } } }}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 Tatoeba Sentence Corpus Scraper from the options below:
If youโd like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: