{
"openapi": "3.0.1",
"info": {
"title": "YouTube Transcript Scraper — SRT/VTT + Whisper AI Fallback",
"description": "Extract YouTube transcripts as plain text, timestamped JSON, SRT or VTT from videos, Shorts, live replays and whole channels. Opt-in Whisper AI transcribes caption-less videos. Lists every caption track, any language, and bills only new uploads on a schedule. Pay only for delivered transcripts.",
"version": "0.0",
"x-build-id": "qJyMUhlJbLAfdfvPB"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/memo23~youtube-transcript-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-memo23-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/memo23~youtube-transcript-scraper/runs": {
"post": {
"operationId": "runs-sync-memo23-youtube-transcript-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/memo23~youtube-transcript-scraper/run-sync": {
"post": {
"operationId": "run-sync-memo23-youtube-transcript-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"startUrls": {
"title": "YouTube video or Shorts URLs",
"type": "array",
"description": "Video URLs in any form — `youtube.com/watch?v=…`, `youtu.be/…`, Shorts or `youtube.com/live/…` replay links — or a channel's `/@handle/videos` page, walked newest first up to Maximum results. Paste as many as you like; each video becomes one transcript row.",
"items": {
"type": "string"
}
},
"datasetId": {
"title": "Dataset ID (chain a scraper run)",
"type": "string",
"description": "Default dataset ID of a finished YouTube scraper run (channel videos, search results, playlists). Every row is deep-scanned for video and channel links, so the row shape does not matter."
},
"datasetItems": {
"title": "Dataset items (paste rows)",
"type": "array",
"description": "Paste rows from a YouTube scraper instead of chaining by ID. Any field holding a youtube.com/watch, youtu.be, /shorts/ or channel URL is picked up."
},
"watchlistId": {
"title": "Watchlist ID",
"type": "string",
"description": "Named key-value store that remembers which videos this run already transcribed. Use the same id on a schedule (for example mkbhd-daily) and later runs leave them out, so a video is never billed twice. Letters, numbers, hyphens, underscores."
},
"newItemsOnly": {
"title": "Only new videos",
"type": "boolean",
"description": "When enabled, videos already stored on the Watchlist ID are left out of the run and the dataset — a channel is still walked, only its new uploads are transcribed. Requires watchlistId. Default: false.",
"default": false
},
"language": {
"title": "Transcript language",
"type": "string",
"description": "Preferred caption language code (e.g. `en`, `de`, `es`). `default` takes the video's original track. When the exact track is missing, YouTube's auto-translate is used where available.",
"default": "default"
},
"whisperFallback": {
"title": "Whisper AI fallback for caption-less videos (premium)",
"type": "boolean",
"description": "When a video has no captions at all, download its audio and transcribe it with Whisper speech-to-text. Billed as a separate premium event per transcribed video — see the pricing tab. Off by default so you never pay it unknowingly. Applies to videos up to 30 minutes long.",
"default": false
},
"maxItems": {
"title": "Maximum results",
"minimum": 1,
"type": "integer",
"description": "Hard cap on transcript rows for the run — your spend guard. Applies per run, across all input URLs (matters for channel expansion).",
"default": 100
},
"maxConcurrency": {
"title": "Max concurrency",
"minimum": 1,
"type": "integer",
"description": "Parallel video fetches.",
"default": 10
},
"minConcurrency": {
"title": "Min concurrency",
"minimum": 1,
"type": "integer",
"description": "Lower bound for the autoscaled pool.",
"default": 1
},
"maxRequestRetries": {
"title": "Max request retries",
"minimum": 0,
"type": "integer",
"description": "Retries per video before it is skipped (skipped videos are never billed).",
"default": 3
},
"proxy": {
"title": "Proxy configuration",
"type": "object",
"description": "Runs go out through the actor's own residential pools, so Apify proxy groups and countries chosen here are not used (the run logs a line saying so). Only your own proxy URLs, with 'Use Apify Proxy' switched off, are honoured.",
"default": {
"useApifyProxy": true
}
}
}
},
"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
}
}
}
}
}
}
}
}
}
}