{
"openapi": "3.0.1",
"info": {
"title": "YouTube Transcript Scraper 📝 (bulk, any language)",
"description": "Transcripts for a whole list of YouTube videos in one run: plain text for your LLM, timed segments for subtitles and search, plus title, channel, duration and views. Picks the language you ask for. Videos with no captions are never charged. No API key, platform usage included.",
"version": "0.1",
"x-build-id": "fbNJg8x53zyZfmjiQ"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/tagadanar~youtube-transcript-extractor/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-tagadanar-youtube-transcript-extractor",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/tagadanar~youtube-transcript-extractor/runs": {
"post": {
"operationId": "runs-sync-tagadanar-youtube-transcript-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/tagadanar~youtube-transcript-extractor/run-sync": {
"post": {
"operationId": "run-sync-tagadanar-youtube-transcript-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"videoUrls"
],
"properties": {
"videoUrls": {
"title": "YouTube video URLs or IDs",
"minItems": 1,
"maxItems": 650,
"type": "array",
"description": "One per line. Watch links (https://www.youtube.com/watch?v=…), short links (https://youtu.be/…), Shorts links, embed links and bare 11-character video IDs all work, and you can mix them. Extra parameters like ?t= or &list= are ignored. Duplicates are removed, so you are never charged twice for the same video.",
"items": {
"type": "string"
}
},
"preferredLanguages": {
"title": "Preferred transcript languages",
"type": "array",
"description": "Language codes in the order you want them, for example en then es. A plain code like en also matches regional tracks such as en-GB. If none of your languages has its own caption track, the transcript is machine-translated into the first one YouTube can translate to, and the row says so. If even that is impossible you still get whatever the video has, flagged with matchedPreferredLanguage: false. Leave empty to always take the video's own default track.",
"default": [
"en"
],
"items": {
"type": "string"
}
},
"includeAutoGenerated": {
"title": "Accept auto-generated captions",
"type": "boolean",
"description": "Most videos only have YouTube's speech-recognition captions. Turn this off to take human-written subtitles only, and skip videos that have none.",
"default": true
},
"outputFormat": {
"title": "Transcript format",
"enum": [
"both",
"text",
"segments"
],
"type": "string",
"description": "Plain text is what you paste into an LLM; timed segments carry a start time and a duration per line, for subtitles, search and video editing.",
"default": "both"
},
"maxVideos": {
"title": "Max videos",
"minimum": 1,
"maximum": 650,
"type": "integer",
"description": "Stop after this many videos, whatever the list contains. Useful when you pipe another scraper's dataset in and want to bound the spend. You are only charged for transcripts actually delivered. The ceiling is 650, which is what a default 3600-second run can actually finish (about 5.5 seconds per video); for more than that, raise the run timeout and split the list across runs.",
"default": 200
}
}
},
"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
}
}
}
}
}
}
}
}
}
}