# Video Ad Analyzer – Competitor Ads: Hook, Angle, Script & Shots (`tubetext/video-ad-analyzer`) Actor

Analyze competitors' video ads with AI. Enter a brand or domain to pull its YouTube video ads from the Google Ads Transparency Center, or chain a Meta / TikTok ad library scraper. Get hook, angle, offer, CTA, script and shot list. $0.05 per ad.

- **URL**: https://apify.com/tubetext/video-ad-analyzer.md
- **Developed by:** [TubeText Labs](https://apify.com/tubetext) (community)
- **Categories:** AI, Videos
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $37.00 / 1,000 ad analyses

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

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 examples already wired to this Actor's own input schema, see the [API](#api) section below.

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`).

# README

## Video Ad Analyzer – Competitor Ads: Hook, Angle, Script & Shots

> By **TubeText Labs** – see all our tools at the end of this page.

Research your competitors' video ads with AI. Type a **brand or domain** and this Actor pulls its video ads from the public **Google Ads Transparency Center** (YouTube ads), watches each one and returns a creative teardown: hook, persuasion angle, offer, pain points, claims, CTA, full script and a shot-by-shot breakdown – plus ideas for variations to test. You can also paste ad video links or **chain a Meta / TikTok ad library scraper**.

Built for media buyers, performance agencies, UGC creators and brand teams who need to know *what* competitors run and *why it might work* – without watching hundreds of ads by hand.

### What you get for every ad

- 🎣 **Hook** – what the viewer sees, reads and hears in the first ~3 s, its type (problem, bold claim, result first…) and why it works
- 🎯 **Angle, offer, pain points, benefits, claims, social proof** – the persuasion strategy, spelled out; offers keep their fine print ("up to", caps, conditions, end dates)
- 🛒 **Products and CTA** – what is sold, when the brand first appears, the call to action and when it lands
- 🎬 **Shot list and structure** – scene, action, on-screen text and spoken words per shot; beats like problem → demo → offer → CTA
- 📝 **Full transcript** (captions or Whisper AI) and editing notes (pacing, measured cuts, captions style)
- 💡 **Variation ideas** your creative team can test
- 📅 **Ad facts** – advertiser, domain, first/last shown dates, Transparency Center link, YouTube link

### Three ways in

1. **`advertisers`** – brand names (`HelloFresh`), domains (`grammarly.com`), advertiser IDs (`AR…`) or Transparency Center advertiser links. Filter by **region** (US, GB, DE…). Newest ads first.
2. **`adUrls`** – ad videos you already have: YouTube, TikTok, Instagram, Facebook or direct `.mp4` links (e.g. video URLs from the Meta Ad Library).
3. **`datasetId`** – the output of an ad library scraper run (Meta / Facebook Ad Library, TikTok ads, Google transparency). Each row's video, advertiser, ad copy, CTA button, landing page and dates are detected automatically; image and text ads are skipped for free.

### Input example

```json
{
  "advertisers": ["grammarly.com", "HelloFresh"],
  "region": "US",
  "maxAdsPerAdvertiser": 10,
  "outputLanguage": "English"
}
```

If you leave out `maxAdsPerAdvertiser` (for example when calling the API), up to **10 ads per brand** are analyzed – about $0.50 per brand.

### Output example

Real output (shortened) for `grammarly.com`:

```json
{
  "status": "ok",
  "advertiserName": "Superhuman Platform Inc.",
  "advertiserDomain": "grammarly.com",
  "creativeId": "CR01613737213038690305",
  "firstShown": "2026-08-27",
  "lastShown": "2026-10-08",
  "transparencyUrl": "https://adstransparency.google.com/advertiser/AR05288677867637440513/creative/CR01613737213038690305",
  "videoUrl": "https://www.youtube.com/watch?v=RkwalS03UBQ",
  "durationSeconds": 15,
  "summary": "A student explains how she uses Grammarly to help manage her heavy workload for an economics group project…",
  "hook": {
    "text": "I'm an economics major. And this group project counts for 50% of my grade.",
    "type": "problem",
    "delivered_as": "voice",
    "why_it_works": "It immediately establishes high stakes and a relatable stressor for the target audience."
  },
  "adFormat": "spokesperson/talking head",
  "offer": "Try Grammarly for free",
  "painPoints": ["high-stakes academic projects", "heavy workload"],
  "benefits": ["AI learning partner", "summarize class notes", "improve work quality"],
  "claims": [{"claim": "Grammarly is an AI learning partner that helps do work better", "support": "demo"}],
  "products": [{"name": "Grammarly", "brand": "Grammarly", "first_seen": 0, "how_shown": "app screen recording"}],
  "cta": {"text": "Try Grammarly for free", "type": "get offer", "time": 13.81},
  "whyItWorks": "It addresses a specific, high-stress pain point for students and immediately provides a clear, functional solution…",
  "suggestions": ["Use a testimonial-style hook from a real student instead of a scripted intro.",
                  "Add a 'before vs. after' comparison of a document edited with Grammarly."],
  "shotCount": 3,
  "shots": ["…"],
  "transcript": "I'm an economics major. And this group project counts for 50% of my grade. Lucky for me…"
}
```

`status` is `ok`, `skipped` (same video as another ad in the run, no video on YouTube, too long – free), `no_ads` or `error` (free). `matchedAs` shows which advertiser or domain a brand name was matched to. Two quality flags help you filter: `advertiserNameContainsBrand` is `false` when the ad was bought by an agency, a legal entity with a different name or a co-branding partner – a hint to double-check, not an error. `languageMatchesRegion` says whether the ad's language is a main language of the region you chose (Google lists ads by where they were shown, so a region can include ads in other languages).

### Pricing

Pay per event:

- **$0.05 per analyzed ad** (cheaper on higher Apify plans: down to $0.037), first 3 minutes included – almost every ad is shorter.
- **$0.01 per extra started minute** for longer videos.
- Listing ads, duplicates, ads without a downloadable video and failed analyses are free.

Example: 10 ads from each of 5 competitors = 50 ads ≈ **$2.50**.

### Tips

- **Brand names vs domains**: a brand name is matched through the brand's official domain first (your region's domain, then `.com`), then by advertiser name, preferring advertisers from the region you chose. `matchedAs` shows what it matched. Big brands often buy ads under a legal entity with another name (Deliveroo in the UK runs as Roofoods Ltd) or through agencies – those ads are kept and flagged with `advertiserNameContainsBrand: false`. For the most precise results, enter the domain (`canva.com`).
- **Languages**: ads in any language are analyzed; choose the output language, and optionally translate quotes. Filter on `languageMatchesRegion` to keep only local-language ads.
- **Monitoring**: schedule a weekly run with your competitor list and compare `firstShown` dates to spot new creatives.
- **Integrations**: run it from n8n, Make, Zapier or the API and send rows to Google Sheets or Notion.

### Ready-made examples

- [Google Ads Transparency Video Ad Analysis](https://apify.com/tubetext/video-ad-analyzer/examples/google-ads-transparency-video-ads)
- [Competitor YouTube Ads Analysis](https://apify.com/tubetext/video-ad-analyzer/examples/competitor-youtube-ads-analysis)
- [Video Ad Script Extractor](https://apify.com/tubetext/video-ad-analyzer/examples/video-ad-script-extractor)
- [Nike YouTube Ads Analysis](https://apify.com/tubetext/video-ad-analyzer/examples/nike-youtube-ads-analysis)
- [HelloFresh YouTube Ads Analysis](https://apify.com/tubetext/video-ad-analyzer/examples/hellofresh-youtube-ads-analysis)
- [Duolingo YouTube Ads Analysis](https://apify.com/tubetext/video-ad-analyzer/examples/duolingo-youtube-ads-analysis)
- [Shopify YouTube Ads Analysis](https://apify.com/tubetext/video-ad-analyzer/examples/shopify-youtube-ads-analysis)
- [Canva YouTube Ads Analysis](https://apify.com/tubetext/video-ad-analyzer/examples/canva-youtube-ads-analysis)
- [Notion YouTube Ads Analysis](https://apify.com/tubetext/video-ad-analyzer/examples/notion-youtube-ads-analysis)

### TubeText Labs tools

**TubeText Labs** builds 9 pay-per-result Apify Actors for video, social and e-commerce data – no login, JSON/CSV/Excel output, and ready for ChatGPT and Claude (Apify MCP), n8n, Make and Zapier. All tools: [apify.com/tubetext](https://apify.com/tubetext)

**Transcripts**

- [YouTube Transcript Scraper](https://apify.com/tubetext/youtube-transcript-fast) – videos, Shorts, playlists and whole channels to text; Whisper AI when there are no captions
- [TikTok Transcript Scraper](https://apify.com/tubetext/tiktok-transcript) – TikTok captions plus Whisper AI, SRT and timestamps
- [Instagram Reels Transcript](https://apify.com/tubetext/instagram-reels-transcript) – reel links or @usernames to text with Whisper AI

**Video & ad analysis**

- [Video Breakdown AI](https://apify.com/tubetext/video-breakdown-ai) – hook analysis, shot list, cut pacing, products shown and script of any TikTok, Reel or YouTube video
- [Video Ad Analyzer](https://apify.com/tubetext/video-ad-analyzer) *(this tool)* – competitors' YouTube video ads by brand or domain (Google Ads Transparency), torn down by AI

**Channel analytics**

- [YouTube Channel Analytics](https://apify.com/tubetext/youtube-channel-analytics) – subscribers, recent video performance, Social Blade grade, ranks and estimated earnings

**E-commerce & travel**

- [TikTok Shop Product Scraper](https://apify.com/tubetext/tiktok-shop-product-scraper) – US TikTok Shop prices, items sold, stock per SKU and shop stats
- [AliExpress Search Scraper](https://apify.com/tubetext/aliexpress-search-scraper) – AliExpress search results by keyword: price, items sold, rating, shipping, badges
- [Google Hotels Scraper](https://apify.com/tubetext/google-hotels-scraper) – hotel prices for any destination and dates, per booking site and as a 90-day price calendar

### FAQ

**Which ads does Google Ads Transparency cover?** Ads run through Google Ads – this Actor analyzes the **video** ones (YouTube ads, including app-install video ads). Text, image and display ads are not analyzed.

**Is the analysis accurate?** It is AI (Google Gemini) watching sampled frames, the transcript and the ad facts. Hooks, offers, CTAs and scripts are usually right; treat strategic fields (angle, why it works, suggestions) as a strong first draft, not ground truth. Song titles are never guessed.

**Is this legal?** The Actor only reads public pages and public ad libraries, without logging in, and collects no personal data. You are responsible for how you use the results (copyright and the platforms' terms).

**How do I get a clean spreadsheet?** In the run's Storage tab choose Export → View: *Overview* for a short set of readable columns in Excel, CSV or Google Sheets. Use JSON to get every field (for example the full shot list).

**Can I cap what a run costs?** Yes – set *Maximum cost per run* in the run options. The run stops cleanly when the next item would go over it: you are never charged more, and you get a clear "stopped at your limit" status message.

**What happens if a big run hits the time limit?** It stops cleanly shortly before the limit: everything finished so far is delivered, the run ends as succeeded, and the status message says how many items weren't started. Raise the run timeout, or run again with the inputs that were not started.

**How do I keep a run from costing more than planned?** Two limits stack: *Max ads per brand* caps how many ads are analyzed for each advertiser, and *Maximum cost per run* stops the run cleanly at your budget. Only video ads are analyzed; image and text ads are skipped for free.

# Actor input Schema

## `advertisers` (type: `array`):

Competitors to research in the Google Ads Transparency Center (YouTube video ads): a brand name (HelloFresh), a domain (grammarly.com), an advertiser ID (AR…) or an adstransparency.google.com advertiser link.

## `maxAdsPerAdvertiser` (type: `integer`):

Video ads analyzed per brand, newest first as listed by Google. For a dataset, the maximum number of ads read from it is 20× this value.

## `region` (type: `string`):

Only ads shown in this country.

## `adUrls` (type: `array`):

Optional: ad videos you already have – YouTube, TikTok, Instagram, Facebook links or direct .mp4 links (e.g. video URLs from the Meta Ad Library).

## `datasetId` (type: `string`):

Optional: chain an ad library scraper (Meta / Facebook Ad Library, TikTok ads, Google transparency). We find each row's video, advertiser, ad copy, CTA, landing page and dates automatically. Image and text ads are skipped for free. Pick the dataset (or paste its ID via API); read-only access to this one dataset is requested.

## `outputLanguage` (type: `string`):

Language of the analysis.

## `translateQuotes` (type: `boolean`):

Off: quotes stay in the ad's original language. On: they are translated into the output language too.

## `includeTranscript` (type: `boolean`):

Adds the ad's spoken words as plain and timestamped text.

## `maxVideoMinutes` (type: `integer`):

Longer videos are skipped (free).

## `maxConcurrency` (type: `integer`):

Ads analyzed in parallel.

## Actor input object example

```json
{
  "advertisers": [
    "grammarly.com"
  ],
  "maxAdsPerAdvertiser": 2,
  "region": "anywhere",
  "adUrls": [],
  "outputLanguage": "English",
  "translateQuotes": false,
  "includeTranscript": true,
  "maxVideoMinutes": 10,
  "maxConcurrency": 5
}
```

# Actor output Schema

## `ads` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "advertisers": [
        "grammarly.com"
    ],
    "maxAdsPerAdvertiser": 2
};

// Run the Actor and wait for it to finish
const run = await client.actor("tubetext/video-ad-analyzer").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "advertisers": ["grammarly.com"],
    "maxAdsPerAdvertiser": 2,
}

# Run the Actor and wait for it to finish
run = client.actor("tubetext/video-ad-analyzer").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "advertisers": [
    "grammarly.com"
  ],
  "maxAdsPerAdvertiser": 2
}' |
apify call tubetext/video-ad-analyzer --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,tubetext/video-ad-analyzer"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/75pa9re3Ox8EbuxAQ/builds/AV0OiQGzvZ6cFqPNS/openapi.json