{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper — Timestamped Chunks", "description": "Extract existing YouTube captions as text, timed segments and source-linked chunks. Current VTT export has known text-escaping and zero-duration cue limitations; use text/segments/chunks while the subtitle fix is validated. Upstream access can fail.", "version": "0.1", "x-build-id": "HNhZrdSTJRCeRwJzo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/keystonelabs~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-keystonelabs-youtube-transcript-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/keystonelabs~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-keystonelabs-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/keystonelabs~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-keystonelabs-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "YouTube videos", "minItems": 1, "maxItems": 100000, "type": "array", "description": "Video URLs or IDs, one per line. Accepts watch URLs, youtu.be links, Shorts, embed URLs and bare 11-character video IDs.", "items": { "type": "string" } }, "language": { "title": "Preferred language", "type": "string", "description": "Preferred caption language, such as en or pt-BR. Exact tracks are preferred, then a broader language variant or another available track unless requireLanguageMatch is on.", "default": "en" }, "translateTo": { "title": "Translate to", "type": "string", "description": "Optional. Language code to machine-translate the transcript into (uses YouTube's own translation). Leave empty to keep the original language." }, "preferManual": { "title": "Prefer human-made captions", "type": "boolean", "description": "When a video has both uploaded and auto-generated captions in the preferred language, use the uploaded ones.", "default": true }, "outputFormats": { "title": "Output formats", "minItems": 1, "type": "array", "description": "Which representations to include in each result. Plain text and timestamped segments are always cheap; SRT and VTT are generated from the same data.", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt" ], "enumTitles": [ "Plain text", "Timestamped segments", "SRT subtitles", "WebVTT subtitles" ] }, "default": [ "text", "segments" ] }, "maxItems": { "title": "Max videos", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many videos.", "default": 100 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many videos to process in parallel. YouTube rate-limits caption downloads per IP, so higher values trigger the automatic proxy fallback more often.", "default": 3 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. The actor already retries through residential proxies automatically if YouTube blocks a request, so you normally leave this off.", "default": { "useApifyProxy": false } }, "includeChunks": { "title": "Include source-linked chunks", "type": "boolean", "description": "Add nested caption chunks with stable IDs, language, timestamps and video links. One dataset row still represents one video.", "default": false }, "chunkMaxCharacters": { "title": "Maximum characters per chunk", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Used when includeChunks is on. Unicode characters are counted; chunk timing stays at source-caption granularity.", "default": 1500 }, "requireLanguageMatch": { "title": "Require the exact caption language", "type": "boolean", "description": "Fail that video with LANGUAGE_UNAVAILABLE unless its caption track exactly matches language, including dialect. Off allows fallback, labeled by languageFallback.", "default": false } } }, "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 } } } } } } } } } }