# Reels & TikTok Hook Analyzer — On-Screen Text & CTAs (`seemuapps/short-video-hook-analyzer`) Actor

Reverse-engineer why a short video works: opening hook and hook type, every on-screen text overlay, CTAs, segment structure, cut pacing and transcript.

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

## Pricing

$100.00 / 1,000 video analyzeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

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

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
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.
Actors are written with capital "A".

## 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.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Reels & TikTok Hook Analyzer

Reverse-engineer why a short video works. Feed in Instagram reel or TikTok URLs and get back the opening hook, every on-screen text overlay, the calls to action, the segment-by-segment structure, edit pacing, and the full transcript — as structured data you can sort and filter.

A plain transcript tells you what was said. This tells you **how the video was built**.

### What you get

Every record is one video:

**The hook**

- `hookText` — the exact opening line that stops the scroll, verbatim
- `hookType` — classified as question, bold claim, problem callout, curiosity gap, result reveal, how-to promise, story open, listicle, direct address and more
- `hookDeliveredAs` — spoken, on-screen text, both, or purely visual
- `hookDurationSeconds` — how long the hook runs before the main content starts
- `hookAnalysis` — a short read on why the opening does or does not hold attention

**On-screen text**

- `onScreenText` — every text overlay with a timestamp, merged into whole phrases rather than word fragments
- `onScreenTextCombined` — all overlays as one string, ready for keyword search
- `hasBurnedInCaptions` — whether subtitle-style captions are burned into the video

**Calls to action**

- `ctas` — each CTA with its timestamp ("follow for more", "link in bio", "comment WORD")
- `ctaCount` — how many CTAs the video contains

**Structure and pacing**

- `structure` — a timestamped breakdown of segment roles: hook → problem → solution → proof → CTA
- `sceneChanges` and `cutsPerMinute` — how aggressively the video is edited
- `isTalkingHead`, `hasVoiceover`, `hasMusic` — the production format
- `contentType` — educational, product promo, testimonial, UGC ad, tutorial, vlog and more
- `topics` — subject keywords

**Post context**

- Username, caption, post date, duration, likes, comments, plays, shares, and a computed `engagementRate`
- `transcript` — full verbatim transcript of the spoken audio

### Use cases

- **Ad creative research** — build a swipe file of hooks that work in your niche, sorted by hook type and engagement rate
- **Hook pattern mining** — analyse 50 top-performing competitor videos and see which opening formulas dominate
- **Content strategy** — compare your videos against creators outperforming you on structure, pacing and CTA placement
- **UGC and creator briefing** — hand creators concrete, evidenced hook formats instead of vague direction
- **Competitive monitoring** — track how a competitor's messaging and offers change across their video output
- **Search and repurposing** — find every video where a phrase appears on screen, not just in the caption

### How to use

1. Paste Instagram reel and/or TikTok video URLs into **Video URLs** (up to 50 per run, both platforms can be mixed)
2. Optionally set a **Language hint** if auto-detection struggles with the audio
3. Leave **Include full transcript** on to get the spoken transcript alongside the analysis
4. Run the actor — results appear in the **Dataset** tab

### Output format

Each dataset record (abbreviated):

```json
{
  "platform": "tiktok",
  "username": "tiktokcreators",
  "postUrl": "https://www.tiktok.com/@tiktokcreators/video/7630922277026090254",
  "durationSeconds": 72,
  "playCount": 50400,
  "engagementRate": 6.38,
  "hookText": "In less than nine months, I went from 200 followers to almost 50,000.",
  "hookType": "result reveal",
  "hookDeliveredAs": "both",
  "hookDurationSeconds": 3,
  "hookAnalysis": "The hook presents a significant achievement and then promises to reveal 'how I did it', creating a strong curiosity gap.",
  "onScreenText": [
    { "start": "00:00", "text": "In less than nine months, I went from 200 followers to almost 50,000." }
  ],
  "ctas": [{ "start": "00:03", "text": "Follow" }],
  "structure": [
    { "start": "00:00", "label": "hook", "summary": "Creator shares his rapid growth on TikTok" },
    { "start": "00:15", "label": "solution", "summary": "Lists essential equipment for high-quality content" }
  ],
  "sceneChanges": 20,
  "cutsPerMinute": 16.7,
  "hasVoiceover": true,
  "hasMusic": true,
  "hasBurnedInCaptions": true,
  "isTalkingHead": true,
  "contentType": "educational",
  "topics": ["TikTok growth", "content creation", "creator tips"],
  "transcript": "In less than nine months, I went from 200 followers to almost 50,000…"
}
```

Export to JSON, CSV, Excel or Google Sheets directly from the Apify console.

### Notes

- Only public Instagram reels and public TikTok videos can be analysed. Private, deleted or restricted posts return an `error` field on their record while the rest of the run continues.
- A video that fails for any reason still produces a record with whatever post metadata was resolved, so nothing silently disappears from your export.
- Videos up to 150 MB are supported. Very long videos with dense captions may exceed what a single analysis response can hold — shorter, feed-style videos are the intended target.

# Actor input Schema

## `videoUrls` (type: `array`):

Instagram reel or TikTok video URLs to analyse, up to 50 per run. Both platforms can be mixed in one run.

## `language` (type: `string`):

ISO 639-1 code of the spoken language, e.g. 'en' or 'es'. Leave as 'auto' to detect it automatically.

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

Include the complete verbatim transcript of the spoken audio alongside the creative analysis.

## Actor input object example

```json
{
  "videoUrls": [
    "https://www.tiktok.com/@tiktokcreators/video/7630922277026090254"
  ],
  "language": "auto",
  "includeTranscript": true
}
```

# Actor output Schema

## `results` (type: `string`):

One video per record. Fields: platform, videoId, postUrl, username, caption, postedAt, durationSeconds, likeCount, commentCount, playCount, shareCount, engagementRate, hookText, hookType, hookDeliveredAs, hookDurationSeconds, hookAnalysis, onScreenText, onScreenTextCombined, transcript, ctas, structure, sceneChanges, cutsPerMinute, hasVoiceover, hasMusic, hasBurnedInCaptions, isTalkingHead, contentType, topics.

# 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 = {
    "videoUrls": [
        "https://www.tiktok.com/@tiktokcreators/video/7630922277026090254"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("seemuapps/short-video-hook-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 = { "videoUrls": ["https://www.tiktok.com/@tiktokcreators/video/7630922277026090254"] }

# Run the Actor and wait for it to finish
run = client.actor("seemuapps/short-video-hook-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 '{
  "videoUrls": [
    "https://www.tiktok.com/@tiktokcreators/video/7630922277026090254"
  ]
}' |
apify call seemuapps/short-video-hook-analyzer --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,seemuapps/short-video-hook-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/Fy9ELxnVOgEQndswd/builds/Fw97WNDKfEJM6bAcG/openapi.json