# TikTok, Reels & Shorts Transcript + AI Hook Analyzer | HookLens (`kuttura_special/hooklens`) Actor

Turn TikTok, Instagram Reels and YouTube Shorts into transcripts plus AI hook analysis: first-3-second hook, 17 hook types, topic, summary, CTA, and engagement/outlier scores. Monitor creators, pay only for new videos, no login. Export JSON/CSV or plug into n8n, Make, or AI agents.

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

## Pricing

Pay per event

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/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

## HookLens: TikTok, Reels & Shorts Transcript + AI Hook Analyzer

🎣 *See exactly why short videos work.*
**By Kuttura LLC · Kuttura Special Projects Division**

Paste TikTok, Instagram Reels or YouTube Shorts links (or a channel/profile or hashtag) and get, for every video:

- **Transcript**: platform captions first, then built-in AI speech-to-text fallback
- **Hook**: the line spoken in the first ~3 seconds (and `hookSource` telling you exactly how it was derived)
- **Topic, summary, CTA**: AI-powered (CTA only when it's an explicit ask to the viewer)
- **Public engagement**: views, likes, comments, shares

Built for **agencies, UGC teams, ad strategists and automation builders** (Make, n8n, Zapier, Clay, custom pipelines) who need structured "why it worked" data, not just view counts.

### Why HookLens

| Feature | What you get | Why it matters |
|---|---|---|
| 🎯 **Hook timing & delivery** | `hookStartSec` (how fast speech starts), `hookDurationSec`, `hookDelivery` = spoken / text-caption / music-only | See whether winners talk in the first second or open on text over a sound |
| 🧩 **Granular hook types** | 17 types: question, bold-claim, contrarian, curiosity-gap, pov, listicle, how-to, before-after, demo, story, skit-humor, social-proof, warning-mistake, relatable, challenge-trend, announcement, other | Build swipe files and A/B test hook formats |
| 📈 **Outlier score** | `engagementRate`, `outlierScore` (views ÷ creator's median), `engagementOutlierScore`, with baselines | Find the videos that over-performed *for that creator*, not just big accounts |
| 🔁 **Monitoring mode** | `onlyNewVideos: true` remembers what it has seen per profile/hashtag | Put it on an Apify Schedule; you **only pay for new videos** |
| 🧠 **Pattern brief** | `generateBrief: true` → one AI strategy brief: common hook types, top performers, patterns, recommendations | A client-ready summary per run for $0.05 |
| ✅ **Honest data** | `hasSpeech`, `hookSource`, `fetchStatus`, validated CTAs (explicit asks only; chants/lyrics rejected) | No invented fields: unknown = `null` |

#### Typical workflows

- **Agency competitor watch:** schedule daily on 10 competitor profiles with `onlyNewVideos` + `generateBrief`, then push `PATTERN_BRIEF` to Slack/Notion.
- **Swipe-file builder:** hashtag → filter `outlierScore >= 3` → export hooks by `hookType`.
- **Automation:** call via the Apify API/webhooks; every field is typed in the dataset schema.

### Input

`videoUrls`, `profile`, `hashtag` + `hashtagPlatform`, `maxVideos`, `language`, `enableStt`, `enableAnalysis`, `forceStt`, `onlyNewVideos`, `generateBrief`, `proxyConfiguration` (datacenter default), `allowResidential` (YouTube only), `residentialCapMb`. See *input_schema.json*.

### Supported platforms

| Platform | Support | Notes |
|---|---|---|
| TikTok | ✅ Full | Videos, profiles, hashtags. Transcript, hook, stats (views, likes, comments, shares) |
| YouTube Shorts | ✅ Full\* | \*YouTube often blocks datacenter IPs. Set `allowResidential: true` (YouTube only, adds $1/1k via `youtube-surcharge`) if results come back `blocked` |
| Instagram Reels | ⚠️ Partial | Caption, likes, comments and audio/transcript are returned. **Views and duration are `null`** when logged out. Instagram profiles/hashtags are not supported (pass Reel URLs) |

HookLens reads spoken audio and captions only. It does **not** read on-screen text (no OCR).

### Output (one row per video)

Real row from a test run on a public TikTok video (Oct 20, 2026), trimmed:

```json
{"platform":"tiktok","stats":{"views":554400000,"likes":514200,"comments":178,"shares":10600},
 "hasSpeech":true,"hook":"Bring my boots in for repair.","hookStartSec":0.06,"hookDurationSec":3,"hookDelivery":"spoken",
 "hookType":"relatable","topic":"Supportive Spouse Role","cta":null,"engagementRate":0.00095,"outlierScore":null,"fetchStatus":"ok"}
```

`outlierScore` is `null` here because it needs at least 3 videos from the same creator in the run.
The run's key-value store also holds `PATTERN_BRIEF` (if enabled) and `RUN_SUMMARY` (proxy usage, processed and skipped counts).

### Pricing (pay per event)

| Event | Price |
|---|---|
| video-processed | $2.00 / 1,000 videos |
| youtube-surcharge | +$1.00 / 1,000 YouTube videos (residential proxy) |
| hook-analysis | $30.00 / 1,000 videos |
| transcription-minute | $0.025 / minute (only when platform captions are missing) |
| pattern-brief | $0.05 per run |
Blocked videos and already-seen videos (monitoring mode) are never charged. No on-screen OCR is performed.

### No API keys needed

You don't need an OpenAI (or any other) API key. AI speech-to-text and AI hook analysis are included in the per-event prices above. Just provide the input and run.

### ⚖️ Legal, GDPR & Terms-of-Service disclaimer

This Actor collects **only publicly available, logged-out data**. It uses no accounts, no cookies tied to a user, and collects no emails or contact details. Public posts may still contain personal data (usernames, voices, faces) under the GDPR/UK GDPR, CCPA and similar laws: **you are the data controller** for what you collect and must have a lawful basis (e.g. legitimate interest), minimise and delete data appropriately, and honour data-subject requests. Scraping may conflict with TikTok, Instagram/Meta or YouTube/Google Terms of Service; you are responsible for your use. Nothing here is legal advice; consult counsel. Kuttura LLC is not affiliated with TikTok, ByteDance, Meta or Google.

# Actor input Schema

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

TikTok, Instagram Reel or YouTube Shorts URLs.

## `profile` (type: `string`):

YouTube channel or TikTok profile URL (Instagram profiles not supported logged-out).

## `hashtag` (type: `string`):

Hashtag without #.

## `hashtagPlatform` (type: `string`):

Hashtag platform.

## `maxVideos` (type: `integer`):

Max videos.

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

Preferred caption language.

## `enableStt` (type: `boolean`):

Used only when no platform captions exist. Billed per minute.

## `enableAnalysis` (type: `boolean`):

Hook/topic/CTA analysis.

## `useBrowser` (type: `boolean`):

Loads logged-out TikTok profile/hashtag pages in Playwright and reads the page's own XHR data.

## `useYtdlp` (type: `boolean`):

yt-dlp for captions/media/metadata.

## `proxyConfiguration` (type: `object`):

Defaults to Apify datacenter proxy. Used by HTTP, Playwright and yt-dlp paths.

## `allowResidential` (type: `boolean`):

Use Apify RESIDENTIAL proxy for YouTube requests only (TikTok/Instagram/Creative Center stay on datacenter). Costs more.

## `forceStt` (type: `boolean`):

Skip platform captions and always transcribe with AI (billed per minute). For QA/testing.

## `residentialCapMb` (type: `integer`):

Estimated residential bytes per run; after the cap, YouTube falls back to datacenter.

## `onlyNewVideos` (type: `boolean`):

Remember processed video IDs per profile/hashtag in the named key-value store 'hooklens-seen'; on later runs skip (and never charge for) already-seen videos. Ideal for Apify Schedules.

## `generateBrief` (type: `boolean`):

After processing, ONE AI call summarizes common hook types, top performers and recommendations into the PATTERN_BRIEF key-value record. Charged once per run (pattern-brief event).

## Actor input object example

```json
{
  "videoUrls": [
    {
      "url": "https://www.youtube.com/shorts/dQw4w9WgXcQ"
    }
  ],
  "hashtagPlatform": "youtube",
  "maxVideos": 10,
  "language": "en",
  "enableStt": true,
  "enableAnalysis": true,
  "useBrowser": true,
  "useYtdlp": true,
  "proxyConfiguration": {
    "useApifyProxy": true
  },
  "allowResidential": false,
  "forceStt": false,
  "residentialCapMb": 50,
  "onlyNewVideos": false,
  "generateBrief": false
}
```

# Actor output Schema

## `overview` (type: `string`):

Per-video hooks, types, CTA, engagement and outlier scores.

## `full` (type: `string`):

All fields including transcripts and timings.

## `patternBrief` (type: `string`):

AI strategy brief per creator (only when generateBrief=true).

## `runSummary` (type: `string`):

Proxy and residential usage, processed and skipped-as-seen counts.

# 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": [
        {
            "url": "https://www.youtube.com/shorts/dQw4w9WgXcQ"
        }
    ],
    "proxyConfiguration": {
        "useApifyProxy": true
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("kuttura_special/hooklens").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": [{ "url": "https://www.youtube.com/shorts/dQw4w9WgXcQ" }],
    "proxyConfiguration": { "useApifyProxy": True },
}

# Run the Actor and wait for it to finish
run = client.actor("kuttura_special/hooklens").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": [
    {
      "url": "https://www.youtube.com/shorts/dQw4w9WgXcQ"
    }
  ],
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}' |
apify call kuttura_special/hooklens --silent --output-dataset

```

## MCP server setup

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

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/mArUL6QXofFeQASB4/builds/HxzeQe8jia6LJTctg/openapi.json