{
"openapi": "3.0.1",
"info": {
"title": "YouTube Transcript Scraper",
"description": "Get YouTube transcripts with timecodes, chapters and video metadata. Works with single videos, playlists and whole channels, returns SRT or WebVTT subtitles, and splits transcripts into RAG chunks that keep their timecodes. Export data, run via API, or schedule runs.",
"version": "0.1",
"x-build-id": "VYvOxazcWpPXwLKvQ"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/lergassy~youtube-transcript-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-lergassy-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/lergassy~youtube-transcript-scraper/runs": {
"post": {
"operationId": "runs-sync-lergassy-youtube-transcript-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/lergassy~youtube-transcript-scraper/run-sync": {
"post": {
"operationId": "run-sync-lergassy-youtube-transcript-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"properties": {
"videos": {
"title": "▶️ Videos, playlists or channels",
"type": "array",
"description": "YouTube video URLs, bare video IDs, playlist URLs or channel URLs. Playlists and channels are expanded into their videos automatically.",
"items": {
"type": "string"
}
},
"language": {
"title": "🔤 Transcript language",
"type": "string",
"description": "Two-letter language code, for example en, de, es. Tracks labelled en-abc123 count as English too.",
"default": "en"
},
"allowAutoGenerated": {
"title": "Use auto-generated captions when needed",
"type": "boolean",
"description": "Fall back to YouTube's automatic captions when the video has no human-written subtitles in that language.",
"default": true
},
"includeSegments": {
"title": "Timed segments",
"type": "boolean",
"description": "Return every caption line with its start time and duration, alongside the full transcript.",
"default": true
},
"chunkForRag": {
"title": "Split into RAG chunks",
"type": "boolean",
"description": "Split the transcript into retrieval chunks. Each chunk carries its chapter title and the timecode where it starts, so an answer can cite the moment in the video.",
"default": false
},
"chunkSize": {
"title": "Chunk size (characters)",
"minimum": 200,
"maximum": 20000,
"type": "integer",
"description": "Target size of one chunk. Chunks break on chapter boundaries and sentence ends, so real sizes vary.",
"default": 1200
},
"chunkOverlapSeconds": {
"title": "Chunk overlap (seconds)",
"minimum": 0,
"maximum": 60,
"type": "integer",
"description": "How many seconds of the previous chunk to repeat at the start of the next one.",
"default": 0
},
"subtitleFormat": {
"title": "Subtitle file",
"enum": [
"none",
"srt",
"vtt"
],
"type": "string",
"description": "Also return a ready-made subtitle file as text.",
"default": "none"
},
"includeDescription": {
"title": "Include the video description",
"type": "boolean",
"description": "Add the full video description to each row.",
"default": false
},
"maxVideosPerChannel": {
"title": "💯 Max videos per channel or playlist",
"minimum": 1,
"maximum": 1000,
"type": "integer",
"description": "How many videos to take from each channel or playlist you pass in.",
"default": 25
},
"maxConcurrency": {
"title": "⚡ Max concurrency",
"minimum": 1,
"maximum": 20,
"type": "integer",
"description": "How many videos to read at the same time.",
"default": 5
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Leave as is. YouTube refuses data-centre addresses, so the Actor uses residential proxies with a fresh address per video.",
"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
}
}
},
"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
}
}
}
}
}
}
}
}
}
}