{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper — Captions, Subtitles & Video Data", "description": "Returns YouTube transcripts (full text + timed segments), language, auto vs manual flag, caption languages, optional translation and video metadata for video, playlist and channel URLs.", "version": "0.1", "x-build-id": "6ZEV0RkVkByaImOAv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tortuga~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tortuga-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tortuga~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-tortuga-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tortuga~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-tortuga-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "urls" ], "properties": { "urls": { "title": "YouTube URLs or video IDs", "type": "array", "description": "One per line. Video URLs (`watch?v=`, `youtu.be/`, `/shorts/`, `/live/`, `/embed/`) or 11-character video IDs, playlist URLs (`/playlist?list=...`), and channel URLs (`/@handle`, `/channel/UC...`, `/c/name`, `/user/name`, optionally ending in `/videos`, `/shorts` or `/streams`). Playlists and channels are expanded to their latest videos.", "items": { "type": "string" } }, "maxVideosPerSource": { "title": "Max videos per playlist / channel", "minimum": 1, "maximum": 5000, "type": "integer", "description": "For each playlist or channel URL, take this many videos (playlist order, or newest first for channels). Video URLs are always processed.", "default": 20 }, "channelTab": { "title": "Channel tab", "enum": [ "videos", "shorts", "streams" ], "type": "string", "description": "Which list a channel URL is expanded from, unless the URL itself ends in `/videos`, `/shorts` or `/streams`.", "default": "videos" }, "language": { "title": "Preferred transcript language", "type": "string", "description": "Language code such as `en`, `de`, `es`, `pt-BR`. A manual (creator-uploaded) track in that language is used first, then an auto-generated one. Leave empty to get the transcript in the video's original spoken language. If the video has no track in this language, the original-language transcript is returned (see **Translate to**)." }, "translateTo": { "title": "Translate to (optional)", "type": "string", "description": "Language code such as `en`, `fr`, `de`, `es`. Adds `translatedTranscript` using a creator-uploaded track in that language when one exists, otherwise YouTube's own auto-translation. YouTube rate-limits auto-translation heavily; the Actor retries on fresh IPs, and `translationStatus` tells you per video whether it worked. Leave empty to skip." }, "includeSegments": { "title": "Include timed segments", "type": "boolean", "description": "Add `segments` (each caption line with `start` and `duration` in seconds) next to the full `transcript` text. Turn off for smaller items when you only need plain text.", "default": true }, "includeVideosWithoutTranscript": { "title": "Include videos without captions", "type": "boolean", "description": "Off (default): videos that have no captions at all are skipped and not charged. On: they are saved with their metadata and `transcriptStatus: no_captions` (charged as a result).", "default": false }, "maxItems": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Stop after this many videos are saved. Each saved video is one charged result, so this caps the cost.", "default": 100 }, "onlyNewOrChanged": { "title": "Only new or changed items", "type": "boolean", "description": "Remember which videos earlier runs of this input returned and output only new videos from the channels and playlists (feed mode). Use with a Schedule; videos already returned are skipped before any request and not charged. Videos skipped for missing captions are tried again on the next run.", "default": false }, "monitoringKey": { "title": "Monitoring key", "type": "string", "description": "Name for this watch, so several schedules on the same channels stay separate; defaults to a key derived from the input" }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Keep Apify RESIDENTIAL proxy: YouTube answers datacenter IPs with 'Sign in to confirm you're not a bot'. Requests are trimmed to a few KB each, so residential traffic is about 25-55 KB per video; total platform usage was about $0.30-0.50 per 1,000 videos in our runs.", "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 }, "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 } } } } } } } } } }