{ "openapi": "3.0.1", "info": { "title": "Douyin 抖音视频转文字 Transcript Scraper - Speech to Text for AI", "description": "Spoken words of any public Douyin video as plain text plus a timed transcript.", "version": "0.2", "x-build-id": "ihaJFSmdIdbnVMFMv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lanternlab318~douyin-transcript/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lanternlab318-douyin-transcript", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lanternlab318~douyin-transcript/runs": { "post": { "operationId": "runs-sync-lanternlab318-douyin-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lanternlab318~douyin-transcript/run-sync": { "post": { "operationId": "run-sync-lanternlab318-douyin-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 videos", "type": "array", "description": "Public Douyin videos, one per line: a video link (https://www.douyin.com/video/7...), a share link (https://v.douyin.com/...), a link carrying modal_id=..., or the bare numeric video ID. Keyword search is not supported here - use the Douyin Search Scraper to find videos first.", "items": { "type": "string" } }, "maxItems": { "title": "Max transcripts per run", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Stop after this many videos. Input lines past the limit are reported as not collected rather than silently dropped.", "default": 1000 }, "includeSegments": { "title": "Include the timed transcript", "type": "boolean", "description": "Add segments[{start, end, text}] - the transcript line by line with a start and end second for each line. Turn it off if you only want the plain text; the row is then smaller but says nothing about timing.", "default": true }, "allowAsr": { "title": "Transcribe the audio when Douyin has no caption", "type": "boolean", "description": "Most Douyin videos carry no caption track. With this on, the Actor downloads the lowest-bitrate rendition and recognizes the speech inside the Actor container with an open-source model - no speech API and no key. With it off, a video without a platform caption comes back with text: null and the reason, and costs nothing.", "default": true }, "language": { "title": "Spoken language", "type": "string", "description": "Leave empty and the model names the language itself, which is what you usually want on Douyin: Mandarin, Cantonese, English, Japanese and Korean come back labelled as what they are. Set a code (zh, yue, en, ja, ko) and that code is reported on every transcribed row instead of the model's own answer; it does not change how the audio is read.", "default": "" }, "maxDurationSec": { "title": "Longest video to transcribe (seconds)", "minimum": 1, "maximum": 7200, "type": "integer", "description": "Videos longer than this are skipped: the row carries the video's metadata, text: null and partialReason transcript:longer_than_maxDurationSec, and is not charged. A video whose length Douyin does not state is treated as over the limit.", "default": 600 }, "maxAudioMb": { "title": "Largest audio download (MB)", "minimum": 1, "maximum": 120, "type": "integer", "description": "Ceiling on one download. The lowest-bitrate rendition of a Douyin video is a few megabytes, so this only catches an outlier.", "default": 40 }, "maxUpstreamRequests": { "title": "Max Douyin requests per run", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Hard ceiling on requests sent to Douyin in this run, retries included. Leave it empty and the Actor works one out from the number of videos you gave it, so a run is never unbounded; 0 sends no request at all. RUN_SUMMARY reports which ceiling was in force." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy for all requests. Off by default: Douyin answers guests without a proxy.", "default": { "useApifyProxy": false } }, "residentialFallback": { "title": "Retry refused videos through a residential proxy", "type": "boolean", "description": "When Douyin refuses the request for a video (captcha, empty answer), retry that video once through an Apify residential proxy exiting in China. Residential traffic costs more than direct requests. A video Douyin does answer about - taken down, private, withheld - is never retried: no exit changes that answer.", "default": true }, "maxFallbackVideos": { "title": "Max videos retried through the residential proxy", "minimum": 0, "maximum": 20, "type": "integer", "description": "Upper limit per run on videos moved to the residential proxy. 0 turns the fallback off.", "default": 3 }, "requestDelaySecs": { "title": "Delay between requests (seconds)", "minimum": 0.2, "maximum": 30, "type": "number", "description": "Minimum pause between two requests from the same guest identity.", "default": 1 }, "maxIdentityRotations": { "title": "Max guest identities per run", "minimum": 0, "maximum": 30, "type": "integer", "description": "How many times a refused request may be retried on a freshly minted guest identity before the video is reported as blocked.", "default": 6 }, "msTokenWaitSecs": { "title": "Wait for the page's security token (seconds)", "minimum": 0, "maximum": 180, "type": "integer", "description": "How long a new guest page may take to receive its security token (msToken) before requests start. Longer waits make requests more likely to be answered.", "default": 20 } } }, "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 } } } } } } } } } }