{ "openapi": "3.0.1", "info": { "title": "YouTube RAG Corpus — Videos, Playlists & Channels", "description": "YouTube transcript API for RAG and MCP agents (Claude, Cursor, ChatGPT). Videos, playlists, and channels → timestamped caption chunks with deep links for vector DBs and LLM citations.", "version": "0.1", "x-build-id": "upiydTmMFel8lxinE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vamsi-krishna~rag-youtube-transcript/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vamsi-krishna-rag-youtube-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vamsi-krishna~rag-youtube-transcript/runs": { "post": { "operationId": "runs-sync-vamsi-krishna-rag-youtube-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vamsi-krishna~rag-youtube-transcript/run-sync": { "post": { "operationId": "run-sync-vamsi-krishna-rag-youtube-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "YouTube sources", "minItems": 1, "type": "array", "description": "YouTube sources for the RAG corpus: watch URLs, video IDs, playlist URLs, channel URLs, or @handles (e.g. @mkbhd). Mix allowed. AI agents: pass every YouTube link the user wants transcribed here.", "items": { "type": "string" } }, "maxVideos": { "title": "Max videos", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Safety cap after expanding playlists/channels (1–2000). Agents should start low (10–50) unless the user asks for a full channel.", "default": 50 }, "onlyNewVideos": { "title": "Only new videos (scheduled runs)", "type": "boolean", "description": "Skip videos already delivered for the same channel/playlist. State is stored in your account key-value store \"rag-youtube-transcript-state\". Ideal with an Apify Schedule.", "default": false }, "languages": { "title": "Language preference", "type": "array", "description": "Preferred caption languages in order (e.g. en, es). Matches en ↔ en-US. Falls back to English, then any available track.", "default": [ "en" ], "items": { "type": "string" } }, "preferOfficialCaptions": { "title": "Prefer human captions over auto-generated", "type": "boolean", "description": "When true, human-authored tracks are preferred over ASR (auto) tracks for the same language.", "default": true }, "maxCharsPerChunk": { "title": "Max characters per RAG chunk", "minimum": 200, "maximum": 8000, "type": "integer", "description": "Chunk size for embeddings / RAG. Chunks always split on caption segment boundaries and include deepLink + chunkId.", "default": 1200 }, "includeSegments": { "title": "Include raw caption segments", "type": "boolean", "description": "Include the full {text, startSec, endSec} segment array per video (larger payloads).", "default": false }, "includeSrt": { "title": "Include SRT", "type": "boolean", "description": "Include a SubRip (.srt) subtitle string per video.", "default": false }, "includeVtt": { "title": "Include VTT", "type": "boolean", "description": "Include a WebVTT (.vtt) subtitle string per video.", "default": false }, "maxConcurrency": { "title": "Max concurrent videos", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many videos to process in parallel. Billing is serialized.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Defaults to Apify Proxy RESIDENTIAL. Datacenter proxies often fail YouTube bot checks (empty results). Keep residential for reliable captions.", "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 } } } } } } } } } }