# YouTube transcript chunks for RAG

**Use case:** 

Turn YouTube videos into RAG-ready transcript chunks. Each chunk has start and end times, text and a deep link to the exact moment in the video, so your LLM can cite sources. Set the chunk size in characters and feed the results straight into a vector database.

## Input

```json
{
  "urls": [
    "https://www.youtube.com/watch?v=T-D1OfcDW1M"
  ],
  "maxVideosPerSource": 20,
  "languages": [
    "en"
  ],
  "fallbackToAnyLanguage": true,
  "outputFormats": [
    "chunks"
  ],
  "chunkSizeChars": 1000,
  "metadataOnly": false,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "RESIDENTIAL"
    ]
  }
}
```

## Output

```json
{
  "url": {
    "label": "Video URL",
    "format": "string"
  },
  "status": {
    "label": "Status",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "channelName": {
    "label": "Channel name",
    "format": "string"
  },
  "durationSec": {
    "label": "Duration (seconds)",
    "format": "integer"
  },
  "publishedDate": {
    "label": "Published date",
    "format": "string"
  },
  "language": {
    "label": "Caption language",
    "format": "string"
  },
  "isAutoGenerated": {
    "label": "Auto-generated captions",
    "format": "boolean"
  },
  "wordCount": {
    "label": "Word count",
    "format": "integer"
  },
  "error": {
    "label": "Error message",
    "format": "string"
  },
  "text": {
    "label": "Transcript text",
    "format": "string"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The YouTube Transcript Scraper: Bulk, Channels, Shorts Actor is ready to run with the inputs already set for "YouTube transcript chunks for RAG". [Sign up or log in](https://console.apify.com/create-task-from-example/41i0lUnkvw9Lod8nN) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "YouTube transcript chunks for RAG" task

The YouTube Transcript Scraper: Bulk, Channels, Shorts Actor will start running based on the input automatically. You can also change all the input fields, like youtube urls or ids, max videos per channel / playlist / search, and more, to match your specific use case.

### 3. Receive the "YouTube transcript chunks for RAG" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as video url, status, title, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "YouTube transcript chunks for RAG" task via API](https://apify.com/jcwilk/youtube-transcripts.md).

## FAQ

### What does a transcript chunk contain?

Each chunk from the YouTube RAG task has an index, start and end time in seconds, the text, and a URL with &t=<seconds>s that jumps to that moment in the video.

### How do I change the chunk size?

Set chunkSizeChars in the YouTube RAG chunk task. It is the approximate maximum characters per chunk, 1,000 here; about 4 characters equal 1 token.

### Can I send the chunks to a vector database?

Yes. The YouTube RAG task outputs JSON you can embed with any model. Run it through the Apify API or n8n, Make, LangChain or LlamaIndex integrations and load the chunks into your store.

### Can I run it from the API, n8n, Make or a schedule?

Yes. The YouTube RAG chunk task runs from the Apify API, schedules and webhooks, and from n8n, Make or Zapier, and returns JSON, CSV or Excel.

## About this Actor

This example demonstrates how to use [YouTube Transcript Scraper: Bulk, Channels, Shorts](https://apify.com/jcwilk/youtube-transcripts.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/jcwilk/youtube-transcripts.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/jcwilk/youtube-transcripts.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`).
