{ "openapi": "3.0.1", "info": { "title": "youtube-transcript-scraper", "description": "Extrae transcripciones de YouTube con análisis de sentimiento, extracción de entidades, métricas SEO y modo compacto optimizado para pipelines RAG/LLM. Soporte multi-idioma con detección automática.", "version": "0.0", "x-build-id": "sz5RStklIMVJLF9tL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vexmeavf~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vexmeavf-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vexmeavf~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-vexmeavf-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vexmeavf~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-vexmeavf-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "videoUrls": { "title": "Video URLs or IDs", "type": "array", "description": "YouTube video URLs or 11-character video IDs. Automatic deduplication.", "items": { "type": "string" } }, "languages": { "title": "Preferred Languages", "type": "array", "description": "Language codes in priority order. 'auto' = try common auto-generated languages.", "items": { "type": "string" }, "default": [ "es", "en", "auto" ] }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of videos to process in this run.", "default": 50 }, "outputFormat": { "title": "Output Format", "enum": [ "captions", "textWithTimestamps", "xmlWithoutTimestamps", "xmlWithTimestamps", "singleStringText", "compact" ], "type": "string", "description": "How to structure the transcript output: captions, timestamps, XML variants, single string, or compact mode for RAG/LLM.", "default": "textWithTimestamps" }, "compactMode": { "title": "Compact Mode", "type": "boolean", "description": "Reduce output size by 50% for LLM/RAG pipelines. Shorter field names, truncated text, essential data only.", "default": false }, "maxRetries": { "title": "Max Retries", "minimum": 1, "maximum": 12, "type": "integer", "description": "Number of retry attempts for failed videos with exponential backoff.", "default": 3 }, "includeSummary": { "title": "AI Summary", "type": "boolean", "description": "Generate a 3-sentence executive summary for each transcript.", "default": true }, "includeSentiment": { "title": "Sentiment Analysis", "type": "boolean", "description": "Analyze positive/negative/neutral sentiment per segment.", "default": true }, "includeEntities": { "title": "Entity Extraction", "type": "boolean", "description": "Extract named entities: persons, organizations, URLs, emails, dates, money.", "default": true }, "includeSEO": { "title": "SEO Metrics", "type": "boolean", "description": "Calculate readability scores, keyword density, and word count.", "default": true }, "includeMetadata": { "title": "Video Metadata", "type": "boolean", "description": "Include video title, channel name, thumbnail URL, and 8 more fields from YouTube oEmbed API.", "default": true }, "freeTier": { "title": "Free videos per run", "minimum": 0, "maximum": 100, "type": "integer", "description": "The first N results of a run are FREE. Beyond that, each result is charged.", "default": 10 } } }, "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 } } } } } } } } } }