{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Full Text + Timestamps for LLMs", "description": "YouTube transcripts from video, channel or playlist links: full plain text ready for an LLM, timed segments, caption language, plus title, channel, publish date, duration, views and every caption language. No login, no cookies. Videos without captions or not public are marked, not charged.", "version": "0.2", "x-build-id": "mX3no2k5gi9uZe19I" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lanternlab318~youtube-transcripts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lanternlab318-youtube-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lanternlab318~youtube-transcripts/runs": { "post": { "operationId": "runs-sync-lanternlab318-youtube-transcripts", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lanternlab318~youtube-transcripts/run-sync": { "post": { "operationId": "run-sync-lanternlab318-youtube-transcripts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "videoUrls" ], "properties": { "videoUrls": { "title": "Video, channel or playlist links", "type": "array", "description": "One entry per line. A video: a watch link (youtube.com/watch?v=...), a short link (youtu.be/...), a Shorts, embed or live link, or a bare 11-character video ID. A channel (youtube.com/@handle or /channel/UC...) or a playlist (youtube.com/playlist?list=...) takes its most recent videos, up to \"Videos per channel or playlist\". Every video produces exactly one row, in the order given. A line that is not a YouTube video, channel or playlist is reported as such and is not charged.", "items": { "type": "string" } }, "maxItems": { "title": "Videos per channel or playlist", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many of a channel's or playlist's most recent videos to take, for each channel or playlist line in the list above. Ignored for single video links.", "default": 10 }, "language": { "title": "Caption language", "type": "string", "description": "Language code of the caption track to return, for example \"en\", \"zh-Hans\" or \"es\". A regional variant matches its base language, so \"en\" also accepts \"en-GB\". Leave empty to take each video's own default track, preferring a human-written track over the auto-generated one. A video that has captions but not in this language is reported with its available languages and is not charged." }, "includeSegments": { "title": "Include the timed segments", "type": "boolean", "description": "On: every row carries segments[] with a start time, an end time and the text of each caption line, so you can link to a timestamp. Off: only the joined plain text and the word count, which keeps the dataset small when you just want to feed the transcript to an LLM.", "default": true }, "maxUpstreamRequests": { "title": "Max YouTube requests", "minimum": 1, "type": "integer", "description": "Hard ceiling on the HTTP requests this run sends to YouTube: caption-list calls, metadata calls, caption downloads, channel pages and retries together. At the ceiling collection stops - the videos not reached are written with partialReason \"upstream_request_cap\" and the run then ends normally. Leave empty and the Actor works a ceiling out from the input, so a run is never unbounded." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "The proxy used for the caption downloads and the channel listing pages. The caption-list call always goes through a residential IP, because YouTube answers datacenter IPs with its \"confirm you are not a bot\" check, and that part is not affected by this setting.", "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 } } } } } } } } } }