{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Subtitles to Text for AI", "description": "Get YouTube video transcripts in bulk: plain text, timestamped segments and AI-ready chunks for RAG. Pick your language, fall back to auto-generated captions, and get video details like channel, views and publish date. $4 per 1,000 transcripts.", "version": "0.1", "x-build-id": "nnt4f2MLfpVcdEeCI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blues_akg~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blues_akg-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/blues_akg~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-blues_akg-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/blues_akg~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-blues_akg-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": [ "videos" ], "properties": { "videos": { "title": "YouTube videos", "type": "array", "description": "One per line. Full URLs (watch, youtu.be, shorts, embed) or bare 11-character video IDs.", "items": { "type": "string" } }, "languages": { "title": "Preferred languages", "type": "array", "description": "Two-letter codes in order of preference, for example en, de, tr. Leave empty to take the video's own captions.", "items": { "type": "string" } }, "allowAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "Most videos have no human-written captions. Turn this off to accept only authored subtitles.", "default": true }, "translateIfMissing": { "title": "Translate when the language is missing", "type": "boolean", "description": "If none of your preferred languages exists, ask YouTube to machine-translate an available track into the first one. Experimental: YouTube currently refuses most translation requests; a refused video is reported and not charged.", "default": false }, "includeTimestamps": { "title": "Include timestamped segments", "type": "boolean", "description": "Adds every caption line with its start time and duration in seconds.", "default": true }, "includeVideoDetails": { "title": "Include video details", "type": "boolean", "description": "Adds channel, length, views, publish date, category, keywords and description. Needs one extra request per video.", "default": true }, "chunkSize": { "title": "Chunk size for AI/RAG (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "0 means no chunking. Set e.g. 1000 to also get the transcript split into overlapping blocks, each with its start time, ready to embed.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How much text each chunk repeats from the previous one, so a sentence split across chunks is not lost.", "default": 200 }, "maxConcurrency": { "title": "Videos fetched in parallel", "minimum": 1, "maximum": 30, "type": "integer", "description": "Lower this if YouTube starts refusing requests.", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "YouTube blocks datacenter IPs with a \"sign in to confirm you're not a bot\" page, so rotating residential proxies are on by default. They are included in the price.", "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 } } } } } } } } } }