{ "openapi": "3.0.1", "info": { "title": "Youtube Transcript Scraper", "description": "Extract transcripts and captions from YouTube videos with language selection support. Returns timestamped segments, full concatenated text, and basic video metadata.", "version": "2.7", "x-build-id": "d43dC8kOy7zazesdW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Video URLs", "minItems": 1, "type": "array", "description": "YouTube video URLs, short links (youtu.be), shorts URLs, or plain video IDs.", "items": { "type": "string" } }, "language": { "title": "Preferred Language", "type": "string", "description": "Preferred transcript language code (e.g., 'en', 'es', 'fr'). Leave empty for default language. If the requested language is not available, the scraper will attempt translation or fall back to the default.", "default": "" }, "includeAutoGenerated": { "title": "Include Auto-Generated Captions", "type": "boolean", "description": "Whether to include auto-generated captions when manual captions are not available.", "default": true }, "useWhisper": { "title": "Use Whisper AI fallback", "type": "boolean", "description": "When YouTube has no transcript (disabled captions, music-only, or blocked), download the audio and transcribe with Whisper AI (faster-whisper, CPU). Adds ~30-180 s per video. Enabled by default to guarantee transcript output even when YouTube captions are unavailable.", "default": true }, "whisperModel": { "title": "Whisper Model", "enum": [ "tiny", "base", "small", "medium", "large-v3-turbo" ], "type": "string", "description": "Whisper model size to use when `useWhisper` is enabled. Larger = more accurate but slower and more RAM. 'base' is balanced.", "default": "base" }, "proxyCountry": { "title": "Proxy Country", "enum": [ "US", "GB", "CA", "AU", "DE", "FR", "JP", "KR", "BR", "IN", "MX", "IT", "ES", "NL", "PL", "SE", "NO", "DK", "FI", "ZA", "SG", "HK", "TW", "ID", "MY", "TH", "PH", "AR", "CO", "CL" ], "type": "string", "description": "Country/region for the proxy IP. Useful if transcripts are geo-blocked in the default US region.", "default": "US" }, "outputFormat": { "title": "Output Format", "enum": [ "full", "text_only", "segments_only" ], "type": "string", "description": "Controls how transcript data is included in the output. 'full' = all fields including segments array. 'text_only' = only full_text (no segments array, smaller output). 'segments_only' = only the segments array (no full_text).", "default": "full" } } }, "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 } } } } } } } } } }