{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper – Timestamped JSON for RAG", "description": "Scrape YouTube transcripts with timestamps, chapters and video metadata as RAG-ready JSON chunks. Bulk video, playlist or channel URLs. No API key.", "version": "0.1", "x-build-id": "CMdOcplQHvf4az3r7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leadsbrary~youtube-transcript-rag-feed/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leadsbrary-youtube-transcript-rag-feed", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leadsbrary~youtube-transcript-rag-feed/runs": { "post": { "operationId": "runs-sync-leadsbrary-youtube-transcript-rag-feed", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leadsbrary~youtube-transcript-rag-feed/run-sync": { "post": { "operationId": "run-sync-leadsbrary-youtube-transcript-rag-feed", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Video / playlist / channel URLs", "type": "array", "description": "YouTube video, playlist or channel URLs. Playlist and channel URLs are expanded into their videos (up to maxResults).", "items": { "type": "string" } }, "videoIds": { "title": "Bare video ids", "type": "array", "description": "11-character YouTube video ids, as an alternative to full URLs.", "items": { "type": "string" } }, "languages": { "title": "Preferred languages", "type": "array", "description": "Preferred caption language codes in priority order. The first available track wins; if none match, the default track is used unless strictLanguage is true.", "default": [ "en" ], "items": { "type": "string" } }, "strictLanguage": { "title": "Strict language match", "type": "boolean", "description": "If true, videos with no caption track in the requested languages get transcriptStatus=\"language_unavailable\" instead of falling back to the default track.", "default": false }, "allowAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "Whether YouTube's automatic speech-recognition caption tracks may be used when no human-authored track exists.", "default": true }, "includeSegments": { "title": "Include cue-level segments", "type": "boolean", "description": "Include the raw cue-level transcript segments with start/end seconds. Disable to keep dataset items small.", "default": true }, "includeChunks": { "title": "Include RAG chunks", "type": "boolean", "description": "Include RAG chunks: cues merged into embedding-sized text blocks with stable ids, timestamps and deep-link URLs.", "default": true }, "chunkMaxChars": { "title": "Chunk max characters", "minimum": 200, "maximum": 8000, "type": "integer", "description": "Target maximum characters per RAG chunk (chunks break on cue boundaries, so the real size may be slightly under).", "default": 1200 }, "chunkOverlapChars": { "title": "Chunk overlap characters", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Characters of overlap carried from the end of one chunk into the next, to avoid cutting sentences across chunk boundaries.", "default": 100 }, "respectChapters": { "title": "Respect chapter boundaries", "type": "boolean", "description": "When chapters are detected, never let a chunk span two chapters and tag each chunk with its chapter title.", "default": true }, "includeChapters": { "title": "Include chapters", "type": "boolean", "description": "Parse the video's chapter markers (from the public description) into a chapters array.", "default": true }, "includeVideoMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Include normalized video metadata (title, channel, publish date, duration, view count, description, keywords) in each item.", "default": true }, "textFormats": { "title": "Extra text formats", "type": "array", "description": "Extra plain-text renderings to attach alongside the JSON.", "items": { "type": "string", "enum": [ "plain", "srt", "vtt", "markdown" ], "enumTitles": [ "Plain text", "SRT", "WebVTT", "Markdown" ] }, "default": [ "plain" ] }, "maxResults": { "title": "Maximum results", "minimum": 0, "type": "integer", "description": "Maximum number of videos to process in the run (safety cap on cost). 0 means no limit.", "default": 25 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum parallel requests. Lower it if YouTube starts rate-limiting.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy settings. Defaults to Residential proxies: YouTube blocks the shared datacenter pool with a \"Sign in to confirm you're not a bot\" challenge. Datacenter proxies can still be selected manually to cut cost, at the risk of that block.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }