{ "openapi": "3.0.1", "info": { "title": "Video Transcript Scraper — YouTube, Vimeo, TED & 1000+ Sites", "description": "Extract video transcripts + metadata from YouTube, Vimeo, TED & 1000+ sites that publish captions, in any language. JSON + LLM-ready Markdown + RAG chunks. No API key. Pay per result. (TikTok/X limited.)", "version": "0.1", "x-build-id": "PMSzWGhPhVSKcFXb3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rikitrader~video-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rikitrader-video-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rikitrader~video-transcript-scraper/runs": { "post": { "operationId": "runs-sync-rikitrader-video-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rikitrader~video-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-rikitrader-video-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "One or more video/audio URLs, OR channel/playlist URLs (expanded into their videos — see Max videos per list). Full transcript support for YouTube, Vimeo, TED, Dailymotion, Rumble, Loom, Twitch and 1000+ sites that publish captions. TikTok/X/Facebook/Instagram are limited (usually require login and rarely expose captions).", "items": { "type": "string" } }, "language": { "title": "Language", "type": "string", "description": "Preferred subtitle language code (ISO, e.g. 'en', 'es', 'fr', 'de', 'pt'). Falls back to the closest available variant (e.g. es → es-419) when the exact code is missing.", "default": "en" }, "includeAutoCaptions": { "title": "Include auto-generated captions", "type": "boolean", "description": "When no human-made subtitle track exists, fall back to the platform's machine-generated captions.", "default": true }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which representations to include in each result. 'chunks' produces token-aware, embedding-ready segments for RAG / conversational agents.", "items": { "type": "string", "enum": [ "json", "text", "markdown", "chunks" ], "enumTitles": [ "JSON (timestamped segments)", "Plain text", "LLM-ready Markdown", "RAG chunks (embedding-ready)" ] }, "default": [ "json", "text", "markdown", "chunks" ] }, "chunkTokens": { "title": "Chunk size (tokens)", "minimum": 50, "maximum": 4000, "type": "integer", "description": "Token budget per RAG chunk (used only when 'chunks' is selected). Enforced with a real tokenizer — see 'Tokenizer' — so it is accurate even for CJK/emoji/code.", "default": 400 }, "tokenizer": { "title": "Tokenizer", "enum": [ "o200k", "cl100k", "chars" ], "type": "string", "description": "Tokenizer for chunk sizing + token_estimate. 'o200k' (GPT-4o / text-embedding-3) and 'cl100k' (ada-002 / GPT-3.5-4) are exact via tiktoken and a good proxy for Claude/Gemini; 'chars' is the fast chars/4 heuristic (under-counts CJK).", "default": "o200k" }, "translateTo": { "title": "Translate to (language code)", "type": "string", "description": "Optionally also return the transcript translated to this language (e.g. 'es', 'fr'). Best-effort and YouTube-only — uses YouTube's auto-translation, which isn't offered for every video/language. Adds a second extraction per video; result appears under 'translated' (null when unavailable)." }, "includeTimestamps": { "title": "Include timestamped segments", "type": "boolean", "description": "Include the per-segment start/end array in the JSON output.", "default": true }, "bestEffort": { "title": "Best effort (emit metadata even without a transcript)", "type": "boolean", "description": "Return a row with metadata (and an 'error' note) even when no transcript is available, instead of skipping the URL.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many videos to process in parallel.", "default": 5 }, "maxVideosPerList": { "title": "Max videos per list", "minimum": 1, "maximum": 200, "type": "integer", "description": "When a channel/playlist URL is given, transcribe at most this many of its videos (most recent first). A total ceiling of 1000 videos per run also applies.", "default": 20 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy settings. Defaults to low-cost DATACENTER proxy (good for TED, Vimeo, Loom, and most sites). For YouTube or high volume, switch on RESIDENTIAL proxy in the selector — YouTube frequently rate-limits or blocks datacenter IPs.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }