{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper – Subtitles to Text for LLM & RAG", "description": "Turn any YouTube video, playlist or channel into clean, LLM-ready text. Full transcripts with timestamps, chapters and video details — 100+ caption languages, no login, no API key.", "version": "0.1", "x-build-id": "kmLz1gn0WTZxSIOGi" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/inovaflow~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-inovaflow-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/inovaflow~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-inovaflow-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/inovaflow~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-inovaflow-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "YouTube URLs (videos, Shorts, playlists, channels)", "type": "array", "description": "Any mix of YouTube links: a video (`watch?v=…`, `youtu.be/…`, Shorts, embed, live), a playlist (`playlist?list=…`), or a whole channel (`/@handle`, `/channel/UC…`, `/c/name`). Bare 11-character video IDs and bare `@handles` work too. Playlists and channels expand to their videos (see \"Max videos per playlist/channel\").", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "language": { "title": "Transcript language", "type": "string", "description": "Language code of the transcript you want, e.g. `en`, `es`, `de`, `pt-BR`, `ja`. Manual captions in that language are preferred over auto-generated ones. Use `auto` to take the video's original spoken language. If the language is not available, the original-language track is used instead (see advanced options).", "default": "en" }, "searchQueries": { "title": "YouTube search queries (optional)", "type": "array", "description": "Instead of (or in addition to) URLs, give search terms — the top matching videos are transcribed, up to \"Max videos per playlist/channel\" per query.", "items": { "type": "string" } }, "maxVideosPerSource": { "title": "Max videos per playlist / channel / search", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Cap for every playlist, channel or search query given above (newest videos first for channels). Single video links are always processed.", "default": 50 }, "includeTimestamps": { "title": "Include timestamped segments", "type": "boolean", "description": "Adds `segments` (start, duration, text) and `timestampedText` (\"[00:12] …\" lines an LLM can cite) to every row, next to the plain `text`.", "default": true }, "includeChapters": { "title": "Split by chapters", "type": "boolean", "description": "When the video has chapters, adds `chapters` — each with its title, start time and its own slice of the transcript. Great for summarising long videos section by section.", "default": true }, "includeMetadata": { "title": "Include publish date, likes & category", "type": "boolean", "description": "Fetches the video's publish date, like count and category (one extra lightweight request per video). Title, channel, duration, views and description are always included.", "default": true }, "subtitleFormats": { "title": "Also produce subtitle files", "type": "array", "description": "Adds ready-to-save `srt` and/or `vtt` subtitle text to each row.", "items": { "type": "string", "enum": [ "srt", "vtt" ], "enumTitles": [ "SRT (SubRip)", "VTT (WebVTT)" ] }, "default": [] }, "includeFailedVideos": { "title": "Keep a row for videos without a transcript", "type": "boolean", "description": "Videos with no captions, private/removed videos and failures still get a row with `status` and `error` explaining why (never charged). Turn off to receive only successful transcripts.", "default": true }, "preferAutoGenerated": { "title": "Prefer auto-generated captions", "type": "boolean", "description": "By default manual (human-made) captions win over YouTube's auto-generated ones when both exist in your language. Turn on to prefer the auto-generated track.", "default": false }, "fallbackToAnyLanguage": { "title": "Fall back to the original language", "type": "boolean", "description": "If the requested language is not available for a video, use its original spoken-language track instead (flagged as `isFallbackLanguage: true`). Turn off to get a `no_transcript` row instead.", "default": true }, "maxConcurrency": { "title": "Max concurrent videos", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many videos are fetched in parallel. Higher is faster but rotates more IPs.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "YouTube blocks most datacenter IPs, so residential proxies are the default. Keep it unless you have your own proxies.", "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 } } } } } } } } } }