{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript & Subtitle Extractor (Batch, Multi-language)", "description": "Extract full transcripts and subtitles from YouTube videos. Supports batch URLs, auto-generated captions, 50+ languages, and timestamped output. Perfect for LLM ingestion, RAG pipelines, and content analysis. $0.01/video.", "version": "0.5", "x-build-id": "xH1yQOcZ80NSaJ1ht" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gochujang~youtube-transcript-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gochujang-youtube-transcript-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/gochujang~youtube-transcript-extractor/runs": { "post": { "operationId": "runs-sync-gochujang-youtube-transcript-extractor", "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/gochujang~youtube-transcript-extractor/run-sync": { "post": { "operationId": "run-sync-gochujang-youtube-transcript-extractor", "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": "YouTube Video URLs or IDs", "type": "array", "description": "List of YouTube URLs or video IDs. Supports full URLs (youtube.com/watch?v=..., youtu.be/...) and bare video IDs.", "default": [ "https://www.youtube.com/watch?v=dQw4w9WgXcQ" ], "items": { "type": "string" } }, "videoUrlsText": { "title": "Paste URLs (one per line)", "type": "string", "description": "Paste multiple YouTube URLs or video IDs, one per line. Merged with the URLs list above — use whichever is more convenient." }, "playlistUrl": { "title": "Playlist or Channel URL", "type": "string", "description": "YouTube playlist URL (youtube.com/playlist?list=...) or channel URL (@handle or /channel/UC...). All videos in the list are processed up to maxVideos. Combined with individual URLs above." }, "maxVideos": { "title": "Max Videos from Playlist/Channel", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of videos to process from a playlist or channel URL. Individual URLs are not affected by this limit.", "default": 50 }, "fetchFullMetadata": { "title": "Fetch Full Metadata (views, upload date, description)", "type": "boolean", "description": "Use yt-dlp to fetch rich metadata per video: view_count, like_count, upload_date (published_at), description, channel_id. Adds ~1-2s per video but completes the normalized schema. Disable if only the transcript is needed.", "default": true }, "languages": { "title": "Preferred Languages", "type": "array", "description": "Language codes in order of preference (e.g. ['en', 'en-US']). Falls back to next if not found.", "default": [ "en" ], "items": { "type": "string" } }, "outputFormat": { "title": "Output Format", "enum": [ "full_text", "timestamped", "segments", "rag_chunks" ], "type": "string", "description": "full_text: single string. timestamped: [0:12] text per line. segments: array of {start, duration, text} objects. rag_chunks: split into word-count chunks for LLM/RAG pipelines.", "default": "full_text" }, "chunkWords": { "title": "Chunk Size (words)", "minimum": 50, "maximum": 2000, "type": "integer", "description": "Only for rag_chunks format. Split transcript into chunks of this many words. Each chunk is a separate dataset item with chunk_index and overlap context.", "default": 300 }, "chunkOverlapWords": { "title": "Chunk Overlap (words)", "minimum": 0, "maximum": 200, "type": "integer", "description": "Words to overlap between consecutive chunks (for context continuity in RAG).", "default": 30 }, "includeTimestamps": { "title": "Include Timestamps in Full Text", "type": "boolean", "description": "Only applies to full_text format — prepend [M:SS] to each line.", "default": false }, "skipIfNoTranscript": { "title": "Skip Videos with No Transcript", "type": "boolean", "description": "When true (default), videos with no available transcript or disabled captions are silently skipped — the run still succeeds. When false, these videos produce an error record in the dataset.", "default": true }, "useApifyProxy": { "title": "Use Apify Residential Proxy", "type": "boolean", "description": "Enable if YouTube blocks requests from Apify's cloud IP. Residential proxy adds ~$0.01-0.05 per run in proxy cost.", "default": false }, "proxyUrl": { "title": "Custom Proxy URL (optional)", "type": "string", "description": "HTTP/HTTPS proxy URL (e.g. http://user:pass@host:port). Leave empty to use Apify proxy or no proxy." } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }