{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Bulk Subtitles, SRT & RAG Chunks", "description": "Extract YouTube transcripts in bulk from videos, playlists, channels, @handles or searches. Timestamped segments, plain text, SRT, VTT and RAG-ready chunks, in any caption language, with optional translation.", "version": "0.1", "x-build-id": "uKeIJTzaib4d5QJuQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamill~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamill-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamill~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-datamill-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamill~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-datamill-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "YouTube videos, playlists, channels or searches", "type": "array", "description": "Paste anything YouTube: video URLs or IDs, `youtu.be` and `/shorts/` links, playlist URLs, channel URLs, `@handles`, or a search with `ytsearch:your query`. Playlists, channels and searches are expanded into their videos automatically, up to **Max videos**.", "default": [ "https://www.youtube.com/watch?v=jNQXAC9IVRw" ], "items": { "type": "string" } }, "maxVideos": { "title": "Max videos", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on how many videos this run will process. Protects you from accidentally pulling an entire channel.", "default": 100 }, "preferredLanguages": { "title": "Preferred caption languages", "type": "array", "description": "Language codes in priority order, e.g. `en`, `ja`, `es`. The first available track wins; `en` also matches `en-GB`. If none match, the video's default track is used.", "default": [ "en" ], "items": { "type": "string" } }, "includeAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "Most videos only have YouTube's automatic captions. Turn this off to accept human-written subtitles only.", "default": true }, "translateTo": { "title": "Translate captions to", "type": "string", "description": "Optional language code (e.g. `ja`, `es`, `de`) to have YouTube translate the captions. If translation is rate limited, you still get the original transcript plus a `translationError` note." }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which representations to include per video. `chunks` produces overlapping passages sized for embeddings, each with its own timestamped YouTube link.", "items": { "type": "string", "enum": [ "segments", "text", "srt", "vtt", "chunks" ], "enumTitles": [ "Timestamped segments", "Plain text", "SRT subtitle file", "WebVTT subtitle file", "RAG chunks (for embeddings)" ] }, "default": [ "segments", "text" ] }, "chunkCharacters": { "title": "Chunk size (characters)", "minimum": 100, "maximum": 20000, "type": "integer", "description": "Target size of each RAG chunk. Only used when `chunks` is selected. Chunks never split a caption line, so timestamps stay exact.", "default": 1200 }, "chunkOverlapCharacters": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How much text each chunk repeats from the previous one, so meaning is not cut at a boundary.", "default": 150 }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Adds title, channel, duration, view count and thumbnail to every item.", "default": true }, "includeDescription": { "title": "Include description and keywords", "type": "boolean", "description": "Adds the full video description and tags. Off by default because descriptions can be very long.", "default": false }, "skipVideosWithoutCaptions": { "title": "Skip videos without captions", "type": "boolean", "description": "When on, videos with no captions are left out of the dataset entirely instead of being reported with a `no_captions` status.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Videos fetched in parallel. Lower this if you hit YouTube rate limits on very large runs.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "**Keep residential proxy enabled.** YouTube blocks datacenter IPs with \"Sign in to confirm you're not a bot\", so runs without a residential proxy will fail. Residential traffic costs roughly $0.0005 per transcript.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }