# Let your agent watch a video

**Use case:** 

Pass a YouTube, TikTok, X, or Instagram link, or an MP4, and get back a timestamped timeline of what is on screen and what is said, as text your agent can act on. Frames and YouTube captions need no API keys. Speech in other videos needs an OpenAI key for Whisper. A 4-minute YouTube video costs about $0.20. Agents call it with run-sync-get-dataset-items and read analysisFull.

## Input

```json
{
  "video": "https://www.youtube.com/watch?v=_f5VEaR-F2k",
  "prompt": "Watch this video and write a timeline another AI can act on. For each scene, give the timestamp (m:ss), what is on screen (people, text, UI, products), and what is said. End with a 3-line summary.",
  "llmProvider": "anthropic",
  "model": "default",
  "skipDestination": true,
  "writeBehavior": "auto",
  "framesToExtract": 0,
  "allowLongVideos": false,
  "forceFreshRun": false,
  "maxChargeUsd": 0.5
}
```

## Output

```json
{
  "completionTimestamp": {
    "label": "Completed",
    "format": "date"
  },
  "sourceUrl": {
    "label": "Source",
    "format": "link"
  },
  "status": {
    "label": "Status",
    "format": "text"
  },
  "analysisMode": {
    "label": "How it watched",
    "format": "text"
  },
  "estimatedCostUsd": {
    "label": "Est. $",
    "format": "number"
  },
  "analysisFull": {
    "label": "Analysis",
    "format": "text"
  }
}
```

## How it works

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

The Video → LLM Analyzer Actor is ready to run with the inputs already set for "Let your agent watch a video". [Sign up or log in](https://console.apify.com/create-task-from-example/7xLSfmEzSuFtVLHz8) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Let your agent watch a video" task

The Video → LLM Analyzer Actor will start running based on the input automatically. You can also change all the input fields, like video, what should the llm do with this video?, and more, to match your specific use case.

### 3. Receive the "Let your agent watch a video" 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 completed, source, status, 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 "Let your agent watch a video" task via API](https://apify.com/grizzlygriff/video-llm-analyzer.md).

## About this Actor

This example demonstrates how to use [Video → LLM Analyzer](https://apify.com/grizzlygriff/video-llm-analyzer.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/grizzlygriff/video-llm-analyzer.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/grizzlygriff/video-llm-analyzer.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`).