{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Bulk & Whole Channels", "description": "Extract transcripts from thousands of YouTube videos in one run. Paste video URLs, a channel, or a playlist. Clean text, timestamped segments, SRT and WebVTT subtitles, or RAG-ready chunks. Any language, human or auto captions, plus video metadata. $2 per 1,000; videos without captions are free.", "version": "0.1", "x-build-id": "kVVeKaLfsb0aW4pRm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gganbukim~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gganbukim-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/gganbukim~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-gganbukim-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/gganbukim~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-gganbukim-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", "required": [ "videoUrls" ], "properties": { "videoUrls": { "title": "YouTube URLs", "type": "array", "description": "Videos, channels or playlists. Paste any mix of: watch URLs, youtu.be links, /shorts/, /embed/, bare 11-character video IDs, @handles, /channel/UC…, or playlist URLs. Channels and playlists are expanded into their videos automatically.", "items": { "type": "string" } }, "maxVideos": { "title": "Max videos", "minimum": 1, "type": "integer", "description": "Hard cap on how many videos this run will process, counting videos pulled out of channels and playlists. Leave empty for no cap.", "default": 100 }, "languages": { "title": "Preferred languages", "type": "array", "description": "ISO-639-1 codes in priority order, e.g. en, es, ko. The first language the video actually has is used. A human-made track always wins over an auto-generated one in the same language.", "default": [ "en" ], "items": { "type": "string" } }, "allowAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "Fall back to YouTube's speech-recognition captions when no human-made track exists. Turn this off if you only want reviewed subtitles.", "default": true }, "anyLanguageFallback": { "title": "Fall back to any available language", "type": "boolean", "description": "If none of your preferred languages exist, take whatever track the video does have instead of returning nothing.", "default": true }, "outputFormat": { "title": "Output format", "enum": [ "text", "chunks", "segments", "srt", "vtt", "all" ], "type": "string", "description": "text = one clean paragraph string. chunks = merged passages sized for RAG/embeddings. segments = raw timed cues. srt / vtt = subtitle files. all = every field at once.", "default": "text" }, "chunkMaxChars": { "title": "Chunk size (characters)", "minimum": 100, "maximum": 20000, "type": "integer", "description": "Only used by the \"chunks\" format. Caption cues are ~2 seconds long and useless for embeddings; this merges them into passages of about this length.", "default": 1200 }, "chunkOverlapChars": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Repeat this much of the previous chunk at the start of the next one, so a sentence split across a boundary still embeds well.", "default": 0 }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Add title, channel, view count, duration, publish date, keywords and thumbnail to every row. Free — it arrives in the same request as the transcript.", "default": true }, "includeEmptyResults": { "title": "Include videos without captions", "type": "boolean", "description": "Emit a row with an error field for videos that have no usable transcript, instead of skipping them silently. You are never charged for these rows.", "default": true }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many videos to fetch in parallel. Raise it for speed, lower it if you see throttling on a small proxy pool.", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Leave the default. YouTube throttles caption downloads per IP, so the actor starts on cheap datacenter proxies and only escalates to residential when it actually gets blocked — that escalation is what keeps the price low.", "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 } } }, "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 } } } } } } } } } }