{ "openapi": "3.0.1", "info": { "title": "Douyin Transcripts Scraper", "description": "Extract public Douyin speech transcripts from URLs, share links or IDs. Get original text, timed cues, optional translation and SRT/VTT/TXT/JSON exports. Use for content analysis; discovery needs a Douyin search tool. $0.019/audio minute; translation adds $0.009/minute, plus platform usage.", "version": "0.1", "x-build-id": "GBU2iadFgEeZY8b3j" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/khadinakbar~douyin-transcripts-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-khadinakbar-douyin-transcripts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/khadinakbar~douyin-transcripts-scraper/runs": { "post": { "operationId": "runs-sync-khadinakbar-douyin-transcripts-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/khadinakbar~douyin-transcripts-scraper/run-sync": { "post": { "operationId": "run-sync-khadinakbar-douyin-transcripts-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", "required": [ "videoUrls" ], "properties": { "videoUrls": { "title": "Douyin video URLs or IDs", "minItems": 1, "maxItems": 100, "type": "array", "description": "Provide public Douyin video links, share text or numeric video IDs. Example: https://www.douyin.com/video/7534679152504376595. Supply 1–100 entries; canonical duplicates are removed. Creator profiles and keyword search belong in separate Douyin Actors.", "items": { "type": "string" } }, "maxVideos": { "title": "Maximum videos", "minimum": 1, "maximum": 100, "type": "integer", "description": "Set the maximum number of unique videos to process. Example: 20. Default 10; range 1–100. Remaining input videos are reported in the run summary.", "default": 10 }, "targetLanguage": { "title": "Translation language", "enum": [ "original", "en", "zh", "es", "hi", "ar", "pt", "ru", "ja", "de", "fr", "ko", "id", "tr", "it", "vi", "th", "nl", "pl", "uk", "fa", "ur", "bn", "ta", "te", "mr", "gu", "kn", "ml", "pa", "ms", "fil", "sw", "he", "el", "ro", "hu", "cs", "sk", "bg", "sr", "hr", "sl", "da", "sv", "no", "fi", "et", "lv", "lt", "ca", "af" ], "type": "string", "description": "Choose an optional translation of the spoken transcript. Example: en for English. Original is the default and preserves the source speech. Both original and translated text are retained when translation succeeds.", "default": "original" }, "transcriptMode": { "title": "Transcript extraction mode", "enum": [ "auto", "speech", "captions" ], "type": "string", "description": "Choose native captions, speech recognition or automatic selection. Example: speech regenerates spoken text from the video audio. Auto tries source captions before speech recognition. Captions mode skips videos with no source subtitle track.", "default": "auto" }, "exportSubtitles": { "title": "Export SRT and WebVTT", "type": "boolean", "description": "Export original and translated subtitles when available. Example: true. Enabled by default with no extra export event. TXT and full JSON exports are retained regardless of this switch.", "default": true }, "includeWordTimestamps": { "title": "Include speech word timestamps", "type": "boolean", "description": "Include word timings returned by speech recognition. Example: true. Disabled by default; native captions have cue timings only. Model estimated timing is not a human verified forced alignment.", "default": true }, "responseFormat": { "title": "Dataset detail level", "enum": [ "detailed", "concise" ], "type": "string", "description": "Choose detailed or concise dataset rows. Example: concise limits transcript previews to 1500 characters and ten cues. Detailed is the default. Full transcripts remain in TXT and JSON exports in both modes.", "default": "detailed" }, "maxDurationMinutes": { "title": "Maximum duration per video", "minimum": 1, "maximum": 30, "type": "integer", "description": "Skip videos longer than this duration. Example: 20 permits a twenty minute video. Default 10; range 1–30 minutes. This universal limit does not depend on the caller account plan.", "default": 10 }, "maxTotalMinutes": { "title": "Maximum audio minutes per run", "minimum": 1, "maximum": 300, "type": "integer", "description": "Cap total billed audio minutes across the batch. Example: 60. Default 30; range 1–300. Each video duration is rounded up to a whole minute before checking the remaining budget.", "default": 30 }, "maxChargeUsd": { "title": "Transcript event budget (USD)", "minimum": 0.001, "maximum": 100, "type": "number", "description": "Set a run budget for transcript and translation events. Example: 1.00. Default 5; range 0.001–100 USD, also limited by the platform max total charge. The platform synthetic start event and compute/proxy/storage usage are additional.", "default": 5 }, "maxRunSeconds": { "title": "Maximum run time (seconds)", "minimum": 60, "maximum": 3600, "type": "integer", "description": "Set an overall execution deadline. Example: 300. Default 900; range 60–3600 seconds. A stopped batch preserves delivered transcripts and reports remaining videos.", "default": 900 } } }, "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 } } } } } } } } } }