{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper — RAG-Ready", "description": "Turn YouTube into RAG-ready transcripts: chapter-grouped, chunk-ready paragraphs for LLM and search pipelines. Re-runs skip already-delivered videos to keep a corpus fresh, and failed videos are never billed. Accepts mixed video, playlist, and channel URLs. Unofficial; public data only.", "version": "0.1", "x-build-id": "J2h7yDCASIZJothNT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vonsensey~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vonsensey-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vonsensey~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-vonsensey-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vonsensey~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-vonsensey-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Video, playlist, or channel URLs", "type": "array", "description": "Mixed list of YouTube URLs. Individual videos, playlists, channels, and @handles are all accepted — each playlist or channel URL is expanded into its videos automatically.", "items": { "type": "string" } }, "languages": { "title": "Preferred languages", "type": "array", "description": "Ordered language preference for the transcript. BCP-47 tags or prefixes are accepted (e.g. \"en\" matches en, en-US, en-GB; \"pt-BR\" matches only Brazilian Portuguese). The first available match wins. Leave empty to take the video's default caption track.", "items": { "type": "string" } }, "allLanguages": { "title": "All languages", "type": "boolean", "description": "Return every available caption track instead of just the best language match. Warning: this returns one dataset item per caption track, and each track is billed as one transcript.", "default": false }, "includeShorts": { "title": "Include Shorts", "type": "boolean", "description": "When expanding channel URLs, also include Shorts. By default channel expansion covers long-form uploads only.", "default": false }, "maxVideosPerSource": { "title": "Max videos per source", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of videos to take from each playlist or channel URL, applied per source URL independently. Direct video URLs are not affected.", "default": 100 }, "includeChapters": { "title": "Include chapters", "type": "boolean", "description": "Extract chapter markers and upload date for each video. Disabling this saves one request per video and leaves uploadDate null.", "default": true }, "formats": { "title": "Extra transcript formats", "type": "array", "description": "Additional rendered formats to include on each dataset item. Structured JSON segments are always included.", "items": { "type": "string", "enum": [ "text", "srt", "vtt" ], "enumTitles": [ "Plain text", "SRT subtitles", "WebVTT subtitles" ] }, "default": [] }, "onlyNewVideos": { "title": "Only new videos", "type": "boolean", "description": "Skip videos already delivered by previous runs sharing the same state label. Useful for scheduled re-runs that should only pick up new uploads.", "default": false }, "stateLabel": { "title": "State label", "type": "string", "description": "Names the persistent delivered-state store used by \"Only new videos\". Runs sharing a label share the same delivered-video memory.", "default": "default" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings for YouTube requests. Residential is the default because YouTube blocks most datacenter IPs for caption fetching (measured ~21% success on datacenter vs ~95% on residential). Keep residential unless you have your own proxy URLs.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "spikeConfig": { "title": "Spike configuration", "type": "object", "description": "Internal: proxy-economics spike configuration. Leave empty." } } }, "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 } } } } } } } } } }