# Video to RAG chunks: transcript and keyframe per scene

**Use case:** 

Transcribe what is said in a video and attach it to the scene it belongs to. Each scene gets its time range, a keyframe link and its words, and the chunks field holds one RAG chunk per scene with speech, ready for embeddings and multimodal search. Example: the first 4 minutes of the Sintel film give 37 scenes and 5 transcript chunks for about $0.11.

## Input

```json
{
  "videoUrls": [
    "https://archive.org/download/Sintel/sintel-2048-surround.mp4"
  ],
  "mode": "scenes",
  "sceneThreshold": 0.3,
  "minSceneSeconds": 1,
  "fastScan": false,
  "intervalSeconds": 10,
  "frameCount": 12,
  "maxFramesPerVideo": 30,
  "skipBlankFrames": true,
  "transcribe": true,
  "language": "en",
  "imageFormat": "jpeg",
  "maxWidth": 1280,
  "quality": 85,
  "contactSheet": true,
  "maxVideoMinutes": 4,
  "maxFileSizeMb": 1000,
  "requestHeaders": {}
}
```

## Output

```json
{
  "url": {
    "label": "URL",
    "format": "link"
  },
  "fileName": {
    "label": "File"
  },
  "durationSec": {
    "label": "Duration (s)",
    "format": "number"
  },
  "sceneCount": {
    "label": "Scenes",
    "format": "number"
  },
  "frameCount": {
    "label": "Frames",
    "format": "number"
  },
  "contactSheetUrl": {
    "label": "Contact sheet",
    "format": "image"
  },
  "billed": {
    "label": "Billed"
  },
  "note": {
    "label": "Note"
  },
  "error": {
    "label": "Error"
  }
}
```

## How it works

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

The Video to Scenes — Scene Detection, Keyframes, Transcript Actor is ready to run with the inputs already set for "Video to RAG chunks: transcript and keyframe per scene". [Sign up or log in](https://console.apify.com/create-task-from-example/LDrcmb1g6warShVlO) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Video to RAG chunks: transcript and keyframe per scene" task

The Video to Scenes — Scene Detection, Keyframes, Transcript Actor will start running based on the input automatically. You can also change all the input fields, like video links, what to extract, and more, to match your specific use case.

### 3. Receive the "Video to RAG chunks: transcript and keyframe per scene" 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 URL, file, duration (s), 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 "Video to RAG chunks: transcript and keyframe per scene" task via API](https://apify.com/saliga/video-to-scenes.md).

## About this Actor

This example demonstrates how to use [Video to Scenes — Scene Detection, Keyframes, Transcript](https://apify.com/saliga/video-to-scenes.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/saliga/video-to-scenes.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/saliga/video-to-scenes.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`).