{ "openapi": "3.0.1", "info": { "title": "TikTok Transcript Scraper", "description": "Get TikTok video transcripts (text, timed segments, SRT) in the original spoken language, from video links or creator handles, plus views, likes and author data. Optional Whisper fallback.", "version": "0.1", "x-build-id": "uix9i6wKo1VTP7NUe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/latentlark~tiktok-transcript/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-latentlark-tiktok-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/latentlark~tiktok-transcript/runs": { "post": { "operationId": "runs-sync-latentlark-tiktok-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/latentlark~tiktok-transcript/run-sync": { "post": { "operationId": "run-sync-latentlark-tiktok-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "videoUrls": { "title": "TikTok video URLs", "type": "array", "description": "One link per line: https://www.tiktok.com/@user/video/123…, vm.tiktok.com / vt.tiktok.com short links, or bare video IDs. Duplicates are removed.", "items": { "type": "string" } }, "profiles": { "title": "Creators (handles or profile URLs)", "type": "array", "description": "e.g. @penniestopounds or https://www.tiktok.com/@penniestopounds. Gets each creator's most recent videos (TikTok's public embed shows about the latest 10).", "items": { "type": "string" } }, "maxVideosPerProfile": { "title": "Max videos per creator", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many recent videos to transcribe per creator. TikTok's public embed exposes roughly the latest 10, so values above ~10 rarely add more.", "default": 10 }, "captionLanguage": { "title": "Caption language", "type": "string", "description": "Leave empty (recommended) to get the original spoken-language transcript. Enter a language code such as 'en' or 'eng-US' to prefer TikTok's machine-translated caption track when it exists; otherwise the original is returned." }, "includeSegments": { "title": "Include timed segments", "type": "boolean", "description": "Add a segments array: [{start, end, text}] in seconds.", "default": true }, "includeSrt": { "title": "Include SRT", "type": "boolean", "description": "Add an SRT subtitle string (ready for video editors and YouTube).", "default": true }, "includeVtt": { "title": "Include WebVTT", "type": "boolean", "description": "Add a WebVTT subtitle string.", "default": false }, "whisperFallback": { "title": "Whisper fallback for videos without captions", "type": "boolean", "description": "Off by default. When on, videos with no TikTok captions are downloaded and transcribed with Whisper (base model is built in). Charged as the higher-priced whisper-transcript event only when it returns speech. Slower than native captions; default 512 MB is fine for base, use 1 GB for small.", "default": false }, "whisperModel": { "title": "Whisper model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "base (default, built in, fast) is good for clear speech. small is more accurate but slower and downloads at run start. tiny is fastest. Use 1 GB memory for small.", "default": "base" }, "maxWhisperVideos": { "title": "Max videos to Whisper", "minimum": 0, "maximum": 500, "type": "integer", "description": "Safety cap: at most this many Whisper transcriptions per run.", "default": 20 }, "whisperMaxDurationSecs": { "title": "Max video length for Whisper (s)", "minimum": 10, "maximum": 1800, "type": "integer", "description": "Skip Whisper for videos longer than this (seconds).", "default": 300 }, "proxyMode": { "title": "Network mode", "enum": [ "auto", "none", "datacenter" ], "type": "string", "description": "Auto (recommended): direct request first, then retries via Apify Proxy with a fresh session if TikTok challenges or rate-limits. Residential proxy is not needed.", "default": "auto" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy used for retries. Apify datacenter proxy (default) is enough.", "default": { "useApifyProxy": true } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 16, "type": "integer", "description": "Videos processed in parallel (1–16).", "default": 8 } } }, "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 } } } } } } } } } }