{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Channels & Playlists", "description": "Bulk YouTube transcripts from videos, whole channels and playlists: publish-date window, language priority with fallback, uploaded vs auto captions, video metadata and only-new-since-last-run.", "version": "0.4", "x-build-id": "s2OjtTm8Jl1WuMFfg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datagrit~youtube-channel-playlist-transcripts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datagrit-youtube-channel-playlist-transcripts", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datagrit~youtube-channel-playlist-transcripts/runs": { "post": { "operationId": "runs-sync-datagrit-youtube-channel-playlist-transcripts", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datagrit~youtube-channel-playlist-transcripts/run-sync": { "post": { "operationId": "run-sync-datagrit-youtube-channel-playlist-transcripts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Videos, channels or playlists", "type": "array", "description": "Any mix of YouTube links and IDs, one per line: video links (watch, youtu.be, Shorts, live, embed) or 11-character video IDs; channel links (https://www.youtube.com/@TED, /channel/UC..., /c/..., /user/...) or bare @handles; playlist links (https://www.youtube.com/playlist?list=PL...) or playlist IDs. A channel link ending in /shorts or /streams reads that tab. A watch link that also carries &list= is read as that single video; use the /playlist?list= link for the whole playlist. If the list is empty, the Actor runs a small free example (3 videos from @TED) and says so in the status message.", "default": [], "items": { "type": "string" } }, "maxItems": { "title": "Maximum transcripts", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many transcripts in total across all sources. Only delivered transcripts count and are charged; rows for videos without captions are free and do not count.", "default": 100 }, "maxVideosPerSource": { "title": "Maximum videos per channel or playlist", "minimum": 0, "maximum": 100000, "type": "integer", "description": "How many videos to take from each channel or playlist (channels newest first, playlists in playlist order). Videos without captions count toward this limit; videos outside the publish-date window, without the title keywords or already delivered by an earlier run do not. 0 = no per-source limit (the run still stops at Maximum transcripts and reads at most 50 listing pages, about 5,000 videos, per source).", "default": 50 }, "channelContent": { "title": "Channel content", "enum": [ "videos", "shorts", "live", "all" ], "type": "string", "description": "Which uploads to read from a channel: long-form videos (the channel's Videos tab), Shorts, live stream replays, or all uploads mixed. A channel link ending in /shorts or /streams overrides this for that channel. YouTube lists only the newest Shorts of a channel (measured: 100 of 520 for @TED); the run status says when a list is shorter than the channel's total.", "default": "videos" }, "publishedAfter": { "title": "Published on or after", "pattern": "^$|^\\d{4}-\\d{2}-\\d{2}([T ][0-9:.]+(Z|[+-]\\d{2}:?\\d{2})?)?$|^\\d{1,4}\\s*(day|week|month|year)s?(\\s+ago)?$", "type": "string", "description": "Only videos published on or after this date (UTC). Use a date like 2026-09-01 or a period back from the run start like 7 days, 2 weeks, 3 months or 1 year. Checked against each video's exact publish date. On channels the listing stops once it reaches older videos. Leave empty for no lower limit.", "default": "" }, "publishedBefore": { "title": "Published before", "pattern": "^$|^\\d{4}-\\d{2}-\\d{2}([T ][0-9:.]+(Z|[+-]\\d{2}:?\\d{2})?)?$|^\\d{1,4}\\s*(day|week|month|year)s?(\\s+ago)?$", "type": "string", "description": "Only videos published before this date (UTC, the day itself excluded), same format as above. Leave empty for no upper limit. On a channel the newer videos still have to be listed first, so a far-back window reads more listing pages.", "default": "" }, "titleKeywords": { "title": "Title keywords", "type": "array", "description": "Only videos whose title contains at least one of these words or phrases (case-insensitive substring match). Leave empty to take every video.", "default": [], "items": { "type": "string" } }, "languages": { "title": "Caption languages", "type": "array", "description": "Caption language codes in order of preference, for example en, es, pt-BR. The first language the video has wins; en also matches en-US and en-GB, and pt-BR also matches pt. Leave empty to take the video's default caption track (usually its spoken language).", "default": [], "items": { "type": "string" } }, "captionType": { "title": "Caption type", "enum": [ "manualFirst", "autoFirst", "manualOnly", "autoOnly" ], "type": "string", "description": "Uploaded (manual) captions are written by the channel; auto-generated captions come from YouTube speech recognition. Choose which to prefer within each language, or accept only one kind.", "default": "manualFirst" }, "languageFallback": { "title": "Fall back to another language", "type": "boolean", "description": "When a video has none of the caption languages above, return its default caption track instead (the row says isLanguageFallback: true). Turn off to get a free row with reason languageNotAvailable instead.", "default": true }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Add the caption lines with start time and duration in seconds (segments). The full plain text (transcriptText) is always included.", "default": true }, "onlyNewSinceLastRun": { "title": "Only videos new since my last run", "type": "boolean", "description": "For scheduled runs. On a channel the Actor remembers every video an earlier run with the same settings read (with or without a transcript) and stops the listing (newest first) at the first of them, so each run returns only the uploads published since the last run; the first run returns the newest videos up to the per-channel limit. Videos in a temporary state are not remembered and are read again next time: upcoming premieres and scheduled live streams, empty caption files, YouTube bot checks, failed requests and videos without a publish date while a date window is set. On a channel they are read again only while they are newer than the stop point. On playlists and single videos, videos whose transcript was already delivered are skipped and videos without a transcript are tried again. The memory is kept per source and per combination of channel content, date window, title keywords, languages and caption settings (plus the optional memory name).", "default": false }, "stateKey": { "title": "Only-new memory name", "type": "string", "description": "Optional name that keeps a separate only-new memory, for example one per schedule or per client. Runs with the same sources, settings and name share the memory.", "default": "" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "YouTube is read through Apify Proxy (datacenter) by default. The Actor switches to a new proxy session when YouTube asks for a sign-in bot check, rate-limits, or returns an empty caption file. If a run fails with a block message, switch to the RESIDENTIAL group.", "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 }, "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 } } } } } } } } } }