# YouTube Transcript Scraper for AI & RAG (LLM-ready)

**Use case:** 

Get clean YouTube transcripts with title, channel and chapters in one flat LLM-ready row per video. No video download, so runs are cheap and fast. Paste video URLs and feed the text to ChatGPT, Claude or your RAG pipeline.

## Input

```json
{
  "startUrls": [
    "https://www.youtube.com/watch?v=UF8uR6Z6KLc",
    "https://www.youtube.com/watch?v=iG9CE55wbtY"
  ],
  "searchQueries": [
    "TypeScript tutorial 2024",
    "cooking recipe pasta"
  ],
  "quality": "1080p",
  "maxFileSizeMb": 200,
  "downloadVideo": false,
  "downloadThumbnail": false,
  "maxVideos": 2,
  "filenameTemplate": "{channelName}_{title}_{quality}",
  "extractMetadata": true,
  "outputFormat": "llm_ready",
  "extractCaptions": true,
  "downloadCaptions": false,
  "captionFormat": "srt",
  "captionLanguage": "en",
  "autoTranslateLanguage": "en",
  "extractComments": false,
  "extractReplies": false,
  "maxComments": 100,
  "extractChannelInfo": false,
  "extractRelatedVideos": false,
  "monitorMode": false,
  "stateStoreName": "my-channel-monitor",
  "webhookUrl": "https://example.com/webhook/youtube-results",
  "maxConcurrency": 4,
  "maxRequestRetries": 3,
  "includeFailedVideos": false,
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}
```

## Output

```json
{
  "videoId": {
    "label": "Video ID",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "transcript": {
    "label": "Transcript",
    "format": "string"
  },
  "wordCount": {
    "label": "Word Count",
    "format": "integer"
  },
  "language": {
    "label": "Language",
    "format": "string"
  },
  "sourceUrl": {
    "label": "Source URL",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [YouTube Video Downloader & Scraper - YouTube All-in-One](https://apify.com/jy-labs/youtube-all-in-one-downloader-scraper.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/jy-labs/youtube-all-in-one-downloader-scraper.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/jy-labs/youtube-all-in-one-downloader-scraper.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).