Chinese Social Media Dataset Translator to English
Pricing
from $2.80 / 1,000 translated rows
Translate supplied Chinese social media datasets to English while preserving hashtags, mentions and emoji. Export pinyin and script variants with row status.
You can access the Chinese Social Media Dataset Translator to English programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "24fW2cCnPCnLg2vXK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zinin~chinese-social-media-dataset-translator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zinin-chinese-social-media-dataset-translator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/zinin~chinese-social-media-dataset-translator/runs": { "post": { "operationId": "runs-sync-zinin-chinese-social-media-dataset-translator", "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/zinin~chinese-social-media-dataset-translator/run-sync": { "post": { "operationId": "run-sync-zinin-chinese-social-media-dataset-translator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "rows": { "title": "Supplied rows", "maxItems": 500, "type": "array", "description": "Inline buyer export, at most 500 objects. Prefill rows are explicitly synthetic demos. Dataset URLs and collection from social platforms are unsupported. Opaque buyer record. Runtime: 64 KiB per row, depth 8, nested arrays at most 100 entries. Unsafe property paths and secret fields are rejected or removed. Runtime object limit: 200 properties.", "items": { "type": "object" } }, "datasetId": { "title": "Buyer dataset ID", "pattern": "^[a-zA-Z0-9]{17}$", "maxLength": 17, "type": "string", "description": "Optional 17-character dataset ID read through your SDK permissions. Omit the inline items/rows property entirely when using this field. No dataset URLs. Pages <=100; total <=5000 rows and 10 MiB. Pick the dataset with the resource picker: under the Actor's limited permissions only a dataset referenced through this field is readable (a dataset ID typed elsewhere fails with dataset_read_failed)." }, "fields": { "title": "Text fields to translate", "maxItems": 20, "type": "array", "description": "Every selected dotted path must be a string. One complete Translated row requires all selected fields and protected spans. No more than 20 paths.", "items": { "type": "string", "maxLength": 80, "minLength": 1 } }, "targetLanguage": { "title": "Target language", "maxLength": 20, "type": "string", "description": "Language code or short label passed to the model, such as en, zh or de. Validate suitability with your selected provider on representative data.", "default": "en" }, "glossary": { "title": "Protected glossary", "maxProperties": 100, "type": "object", "description": "At most 100 source-to-output mappings, each key and value <=100 characters. Longest source terms win. Protected spans are restored to the mapped value.", "default": {} }, "batchSize": { "title": "Rows per LLM call", "minimum": 1, "maximum": 10, "type": "integer", "description": "At most 10. Batches shrink before requests to fit byte/token units and the number of rows the current buyer budget can cover.", "default": 5 }, "includePinyin": { "title": "Include source pinyin", "type": "boolean", "description": "Generate pinyin locally from the original Chinese text. Names, polyphonic characters and regional usage can need human review.", "default": true }, "scriptMode": { "title": "Source script conversion", "enum": [ "none", "traditional", "simplified" ], "type": "string", "description": "Convert original source strings to traditional or simplified Chinese using OpenCC, or choose none. These fields describe source text, not the translated answer.", "default": "traditional" }, "detectLanguage": { "title": "Include language heuristics", "type": "boolean", "description": "Use visible script to label zh, en, zh+en or und. Dialect markers are explicitly heuristic with null confidence; no identity or origin inference.", "default": true }, "maxItems": { "title": "Maximum processed source rows", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Count of source rows considered in this run, including free failures. Platform maximum 20; dataset ingestion independently caps at 5000 rows and 10 MiB.", "default": 5 }, "apiKey": { "title": "Buyer API key (optional)", "type": "string", "description": "Optional buyer credential for the selected endpoint. Never copied to results. Empty uses the platform key only with OpenRouter. Buyer credentials are never replaced after a provider error. Runtime limit: 512 characters." }, "baseUrl": { "title": "OpenAI-compatible base URL", "maxLength": 300, "type": "string", "description": "HTTPS base path, without /chat/completions. Only documented host/path pairs are accepted. Custom native endpoints require apiKey. Search supports OpenRouter only. No query, credentials, fragments or redirects.", "default": "https://openrouter.ai/api/v1" }, "model": { "title": "Model ID", "maxLength": 100, "type": "string", "description": "Keyless: deepseek/deepseek-v4-flash or z-ai/glm-5.3-flash only. Qwen, Kimi and other model IDs require BYOK. The provider must support this model and operation.", "default": "deepseek/deepseek-v4-flash" }, "reasoningMode": { "title": "Thinking mode (OpenRouter)", "enum": [ "off", "low", "provider" ], "type": "string", "description": "OpenRouter only: off disables thinking, or uses low effort for z-ai/ models. Off-mode HTTP 400 retries with low effort, then provider defaults, within run caps. Direct endpoints retain provider thinking settings.", "default": "off" }, "maxOutputTokens": { "title": "Maximum completion tokens", "minimum": 1, "maximum": 4096, "type": "integer", "description": "Upper completion allowance per call, including reasoning tokens. Default 768; platform hard maximum 1024; BYOK hard maximum 4096. Length-truncated answers are free incomplete results.", "default": 768 }, "maxTotalTokens": { "title": "Run token-unit limit", "minimum": 1, "maximum": 2000000, "type": "integer", "description": "UTF-8 message bytes plus completion reserve before each attempt, reconciled with valid usage afterward. Platform hard maximum 40000; BYOK 2000000. Unknown usage consumes full reserve.", "default": 40000 }, "temperature": { "title": "Temperature", "minimum": 0, "maximum": 2, "type": "number", "description": "Sampling temperature passed to the provider. Repeated runs can differ even at a low value. Does not establish factual correctness.", "default": 0.2 }, "maxConcurrency": { "title": "Concurrent LLM calls", "minimum": 1, "maximum": 1, "type": "integer", "description": "Version 1 processes one call at a time. Billing and delivery are serialized. Schedule citation comparisons without overlapping runs.", "default": 1 } } }, "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 Chinese Social Media Dataset Translator to English 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: