{ "openapi": "3.0.1", "info": { "title": "Youtube Transcript Scraper", "description": "Extract full transcripts from YouTube videos with the YouTube Transcript Scraper. Get precise timestamps, speaker names, and text for any video. Perfect for content analysis, SEO, research, and summarization. Fast, accurate, and easy to integrate into your workflow.", "version": "0.1", "x-build-id": "UDAWuAy3swCEooy9T" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapier~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapier-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapier~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-scrapier-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapier~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-scrapier-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "YouTube Video URLs πŸ”—", "type": "array", "description": "Add one or more YouTube links to extract transcripts from. Each completed video appears in your dataset automatically. ⚑", "default": [], "items": { "type": "string" } }, "includeEnglishAG": { "title": "Include English Auto-Generated πŸ‡ΊπŸ‡Έ", "type": "boolean", "description": "Enable to include English auto-generated transcripts when available.", "default": true }, "includeNonEnglish": { "title": "Include Non-English Transcripts 🌍", "type": "boolean", "description": "Enable to include transcripts in languages other than English.", "default": false }, "outputFormat": { "title": "Output Format πŸ“", "enum": [ "timestamp", "text" ], "type": "string", "description": "Choose transcript style: 'timestamp' includes time markers, while 'text' returns clean plain text.", "default": "text" }, "fetchVideoMetadata": { "title": "Fetch Real Video Metadata πŸ“Š", "type": "boolean", "description": "Fetch title, channel name/ID/URL, publish date, category, tags, thumbnails, duration, view count, like count, and live-status directly from the YouTube watch page. Default is false (base transcript-only behavior). When off, none of the metadata fields are added to the output.", "default": false }, "includeEngagementMetrics": { "title": "Compute Engagement Analytics πŸ“ˆ", "type": "boolean", "description": "Adds engagementRate (likes Γ· views), estimatedSpeakingRateWpm (transcript words per minute of runtime), and transcriptCoveragePercent (caption coverage of the video's runtime) β€” all computed locally from the harvested metadata + transcript, no extra AI cost. Requires video metadata to be fetched (auto-enabled if this or channel info is on). Default is false.", "default": false }, "includeChannelInfo": { "title": "Include Channel Subscriber Count (Best-Effort) πŸ“Ί", "type": "boolean", "description": "Best-effort extra request to the channel's 'About' page for its subscriber count. Automatically also fetches video metadata (needed to resolve the channel). Coverage is partial (not guaranteed for every channel) β€” reported as-is, never fabricated. Default is false.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration 🌐", "type": "object", "description": "Optional proxy setup for stable access. Uses Apify Residential Proxy by default when needed.", "default": {} } } }, "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 } } } } } } } } } }