{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper for AI & RAG – Videos, Channels", "description": "Get YouTube transcripts (captions) in bulk from videos, playlists, channels or search. Clean text, timestamped segments and RAG-ready chunks with deep links, language fallback and video metadata. Pay only for successful transcripts.", "version": "0.1", "x-build-id": "gxlY4CCPznDFIV5AG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/clearfeed-labs~youtube-transcripts-ai/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-clearfeed-labs-youtube-transcripts-ai", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/clearfeed-labs~youtube-transcripts-ai/runs": { "post": { "operationId": "runs-sync-clearfeed-labs-youtube-transcripts-ai", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/clearfeed-labs~youtube-transcripts-ai/run-sync": { "post": { "operationId": "run-sync-clearfeed-labs-youtube-transcripts-ai", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "YouTube URLs or IDs", "type": "array", "description": "Any mix of video URLs (watch, youtu.be, Shorts, live, embed), bare 11-character video IDs, playlist URLs, and channel URLs or @handles (e.g. https://www.youtube.com/@3blue1brown). Duplicates are removed.", "items": { "type": "string" } }, "searchQueries": { "title": "Search queries (optional)", "type": "array", "description": "Find videos by YouTube search and get their transcripts, e.g. \"retrieval augmented generation tutorial\".", "items": { "type": "string" } }, "maxVideosPerChannel": { "title": "Max videos per channel", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Newest videos taken from each channel.", "default": 20 }, "channelTabs": { "title": "Channel tabs", "type": "array", "description": "Which channel tabs to take videos from (used when the channel URL has no tab).", "items": { "type": "string", "enum": [ "videos", "shorts", "streams" ], "enumTitles": [ "Videos", "Shorts", "Live streams" ] }, "default": [ "videos" ] }, "maxVideosPerPlaylist": { "title": "Max videos per playlist", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Videos taken from each playlist, in playlist order.", "default": 100 }, "maxVideosPerSearch": { "title": "Max videos per search query", "minimum": 1, "maximum": 500, "type": "integer", "description": "Top search results taken for each query.", "default": 20 }, "maxVideos": { "title": "Max videos in total", "minimum": 0, "type": "integer", "description": "Hard cap across all inputs. 0 = no cap.", "default": 0 }, "languages": { "title": "Preferred languages", "type": "array", "description": "Language codes in order of preference (e.g. en, de, es, pt-BR). 'en' also matches en-US/en-GB. Uploaded (human) captions are preferred over auto-generated ones in the same language.", "default": [ "en" ], "items": { "type": "string" } }, "allowAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "Use YouTube's automatic (speech recognition) captions when no uploaded captions exist in your languages.", "default": true }, "allowTranslation": { "title": "Translate when your language is missing (experimental)", "type": "boolean", "description": "If no track exists in your preferred languages, ask YouTube for a machine translation into the first preferred language. YouTube currently rate-limits translated captions heavily, so this usually falls back to the original language (see translationError).", "default": false }, "fallbackToAnyLanguage": { "title": "Fall back to the original language", "type": "boolean", "description": "If nothing above works, return the transcript in whatever language is available (the spoken language first) instead of an error.", "default": true }, "outputMode": { "title": "Output rows", "enum": [ "video", "chunk" ], "type": "string", "description": "One row per video, or one row per text chunk (ready to embed and load into a vector database).", "default": "video" }, "includePlainText": { "title": "Plain text", "type": "boolean", "description": "Full transcript as one clean string.", "default": true }, "includeTimestampedText": { "title": "Timestamped text", "type": "boolean", "description": "Transcript as paragraphs prefixed with [mm:ss], about every 30 seconds. Great for LLM answers with citations.", "default": false }, "includeSegments": { "title": "Timestamped segments", "type": "boolean", "description": "Array of caption lines with start and end in seconds.", "default": false }, "includeChunks": { "title": "Chunks (in per-video rows)", "type": "boolean", "description": "Add a `chunks` array to each video row. Always on in per-chunk mode.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 50000, "type": "integer", "description": "Target chunk length. ~4 characters ≈ 1 token, so 2000 ≈ 500 tokens. Chunks never cut a caption line.", "default": 2000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Characters repeated at the start of the next chunk so context is not lost at boundaries.", "default": 200 }, "removeNonSpeechTags": { "title": "Remove non-speech tags", "type": "boolean", "description": "Strip [Music], [Applause], ♪ and similar tags.", "default": true }, "includeMetadata": { "title": "Video metadata", "type": "boolean", "description": "Title, channel, publish date, duration, views, category, keywords, thumbnail.", "default": true }, "includeDescription": { "title": "Video description", "type": "boolean", "description": "Add the full video description text.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Videos processed in parallel.", "default": 10 }, "maxRetries": { "title": "Attempts per video", "minimum": 1, "maximum": 10, "type": "integer", "description": "Each retry uses a fresh IP address.", "default": 6 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Residential Apify Proxy is the default because YouTube blocks most datacenter IPs. Only small caption files (~30 KB per video) go through it. If you choose datacenter proxies, blocked videos are retried through residential IPs automatically.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "residentialFallback": { "title": "Automatic residential fallback", "type": "boolean", "description": "Retry blocked videos through residential IPs.", "default": 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 }, "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 } } } } } } } } } }