{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper With AI Insights", "description": "YouTube Transcript Scraper: Extract video transcripts with titles, channels, timestamps, and video URLs. Generate AI-powered insights to identify key topics, keywords, summaries, audience themes, and content patterns for research, SEO, and content strategy.", "version": "0.1", "x-build-id": "Bz2kZG9Je4uYFxG5b" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/api-empire~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-api-empire-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/api-empire~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-api-empire-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/api-empire~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-api-empire-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "πŸ”— Target Video URLs", "type": "array", "description": "πŸ“‹ One or more YouTube video URLs to extract transcripts from and distill. Example: https://www.youtube.com/watch?v=4KbrxIpQgkM. (Also accepts the base actor's `urls` key.)", "items": { "type": "string" } }, "excludeAutoGeneratedCaptions": { "title": "πŸš«πŸ‡ΊπŸ‡Έ Exclude Auto-Generated English Captions", "type": "boolean", "description": "Leave unchecked (default) to include English auto-generated caption tracks, matching the base actor's default. Check to exclude them. (Base equivalent: `includeEnglishAG: false`.)" }, "includeTranslatedCaptions": { "title": "🌍 Include Non-English Captions", "type": "boolean", "description": "Include caption tracks in languages other than English. Unchecked (default) excludes them, matching the base actor's default. (Also accepts `includeNonEnglish`.)" }, "transcriptFormat": { "title": "πŸ“ Transcript Output Shape", "enum": [ "timestamp", "text" ], "type": "string", "description": "'timestamp' returns cue-level start/end times; 'text' returns one clean text blob per language. Default 'text'. (Also accepts `outputFormat`.)" }, "enableAiInsights": { "title": "✨ Enable AI Insights", "type": "boolean", "description": "When ON, sends the primary transcript to an AI provider to generate `aiSummary`, `aiKeyPoints`, and `aiTopics`. Requires `aiApiKey` (or a matching provider env var) β€” with no key, these fields stay `null` and the rest of the actor still runs normally. OFF by default.", "default": false }, "insightDepth": { "title": "πŸ“ Insight Depth", "enum": [ "short", "medium", "long" ], "type": "string", "description": "Controls how detailed the AI summary/key-points/topics are. 'short' = 2-3 sentence summary + 3 key points + 3 topics. 'medium' = 4-6 sentences + 5 + 5. 'long' = multi-paragraph + 8 + 8. Default 'medium'. Ignored when AI insights are off.", "default": "medium" }, "aiProvider": { "title": "🧠 AI Provider / Model", "enum": [ "claude-haiku-4-5", "claude-sonnet-5", "claude-opus-4-8", "claude-fable-5", "gpt-4o-mini", "gpt-4o", "gpt-4.1-mini", "gpt-4.1", "o3-mini", "o1", "gemini-2.0-flash-lite", "gemini-2.0-flash", "gemini-1.5-pro", "gemini-2.5-flash", "gemini-2.5-pro", "grok-2-latest", "grok-3-mini", "grok-3", "grok-beta", "deepseek-chat", "deepseek-reasoner", "sonar", "sonar-pro", "sonar-reasoning", "mistral-small-latest", "mistral-large-latest" ], "type": "string", "description": "Model to use for AI insights; the provider is auto-detected from the name: claude-*=Anthropic, gpt-*/o1/o3=OpenAI, gemini-*=Google, grok-*=xAI, deepseek-*=DeepSeek, sonar*=Perplexity, mistral-*=Mistral. Cheaper mini/flash/haiku models are recommended. Ignored when AI insights are off.", "default": "claude-haiku-4-5" }, "aiApiKey": { "title": "πŸ”‘ AI Provider API Key", "type": "string", "description": "πŸ”’ API key for the selected provider. If left empty, falls back to the matching environment variable (ANTHROPIC_API_KEY / OPENAI_API_KEY / GEMINI_API_KEY or GOOGLE_API_KEY / XAI_API_KEY or GROK_API_KEY / DEEPSEEK_API_KEY / PERPLEXITY_API_KEY or PPLX_API_KEY / MISTRAL_API_KEY). With no key available anywhere, AI fields are simply `null` β€” never faked." }, "proxyConfiguration": { "title": "🌐 Proxy Configuration", "type": "object", "description": "Optional proxy setup for stable access. Uses Apify Residential Proxy by default when needed to bypass YouTube IP blocking." } } }, "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 } } } } } } } } } }