# TikTok & Reels Script Analyzer: Hook, Structure, Score & Tips (`spokentext/tiktok-reels-script-analyzer`) Actor

Paste TikTok, Instagram Reels or YouTube Shorts links and get each video's script analysed: the hook in the first 3 seconds, its strength, the structure, the call to action, a score out of 10 and concrete tips, plus pace, filler words and the transcript.

- **URL**: https://apify.com/spokentext/tiktok-reels-script-analyzer.md
- **Developed by:** [clement](https://apify.com/spokentext) (community)
- **Categories:** Social media, AI, Videos
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $32.00 / 1,000 script 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

### What is TikTok & Reels Script Analyzer?

**TikTok & Reels Script Analyzer** reviews the script of short videos like a content strategist would. Paste TikTok, Instagram Reels or YouTube Shorts links, yours or your competitors', or **a TikTok creator's profile link** (`https://www.tiktok.com/@name`) to analyse their latest videos, and for each video you get:

- the **hook**: the words spoken in the first 3 seconds, its type and a **hook strength score**
- **2 or 3 better hooks** for the same video
- the **structure** of the script, part by part, with times: hook, problem, value, proof, story, offer, call to action
- the **call to action**, or a note that there is none
- an **overall score out of 10**, what works, and **concrete improvements**
- **speech figures**: words per minute, filler words (um, uh, euh...), words repeated as tics, long pauses, and how fast the first word comes
- the **full transcript**, plus the creator, caption, views and likes

It is built for content creators, social media managers, UGC creators and agencies who want to understand why videos work, and to make their own better.

### Why use it?

- **Feedback you can act on:** a better hook to film, the intro to cut, the call to action to add.
- **Competitor research:** run a competitor's best videos and see the hooks and structures they rely on.
- **Real speech figures:** filler words and pauses are counted from word timings, not guessed. The transcript keeps hesitations instead of tidying them away.
- **Works on videos without captions:** the speech itself is transcribed, in 99+ languages.
- **No login, no cookies:** public videos only.
- **Pay per video.** No subscription.

Because it runs on Apify, you also get scheduling, API access, integrations (Make, Zapier, n8n, Google Sheets, Notion via integrations) and exports to JSON, CSV or Excel.

### How to use it

1. Paste one or more **TikTok or Instagram Reels links**, one per line.
2. Optionally set the **analysis language**, for example French for feedback in French on an English video.
3. Click **Start**. The **Output** tab shows each video's score, hook, structure and improvements.

On the free Apify plan, each run transcribes and analyses up to 10 minutes of audio in total, which covers about ten short videos. Paid Apify plans have no such limit.

### How much does it cost?

| | Price (Bronze) |
|---|---|
| Per video analysed | $0.04 |
| Per minute of audio transcribed | $0.0027 |

A 30-second video costs about $0.043 and a 90-second one about $0.045. Silver and Gold tiers pay less. Videos that fail to download are not charged, and an analysis that fails is not charged either.

### Input example

```json
{
    "urls": [
        "https://www.tiktok.com/@nasa/video/7700397098994273549",
        "https://www.instagram.com/reel/CqlKdduP1p-/"
    ],
    "analysisLanguage": "English"
}
```

### Output example

Real result for NASA's 17-second TikTok above, captured on 2026-11-05 (shortened):

```json
{
    "platform": "TikTok",
    "creator": "NASA",
    "durationSeconds": 17,
    "score": 4,
    "hookText": "All righty. Hello, everybody. You got, uh, Dick Burns and Doug Jemko",
    "hookType": "direct address",
    "hookStrength": 2,
    "hookFeedback": "The greeting and speaker introductions take up the opening seconds without giving viewers a reason to stop scrolling. The NASA-Alabama connection and “Roll Tide” arrive later, and the caption supplies more context than the spoken hook.",
    "betterHooks": [
        "NASA just brought a little extra lift to Alabama football.",
        "NASA and the Crimson Tide: ready for an air show?"
    ],
    "structure": [
        { "part": "hook", "startSeconds": 0, "summary": "..." },
        { "part": "context", "startSeconds": 3, "summary": "..." },
        { "part": "other", "startSeconds": 9, "summary": "..." }
    ],
    "callToAction": null,
    "improvements": [
        "Open with the NASA-Alabama connection or the Flywheel itself; cut the greeting and introductions.",
        "Explain or visually clarify what the “NASA Flywheel” is, since the phrase may not mean much to viewers on its own.",
        "Add a simple engagement prompt, such as asking viewers who they’re cheering for."
    ],
    "speech": {
        "wordsSpoken": 34,
        "wordsPerMinute": 165,
        "firstWordAtSeconds": 0.1,
        "hesitations": { "total": 1, "perMinute": 4.8, "byWord": { "uh": 1 } },
        "verbalTics": {},
        "longPauses": [{ "atSeconds": 6.7, "seconds": 2.3 }]
    },
    "text": "All righty. Hello, everybody. You got, uh, Dick Burns and Doug Jemko here. We just got done doing the NASA Flywheel for the University of Alabama, huh? Super proud to show support. Roll Tide!",
    "analysisIsAiGenerated": true
}
```

| Field | Meaning |
|---|---|
| `score` | Overall strength of the script for short-form video, 1 to 10 |
| `hookText` | The words spoken in the first 3 seconds |
| `hookType`, `hookStrength`, `hookFeedback` | What kind of hook it is, how strong (1 to 10) and why |
| `betterHooks` | Stronger opening lines for the same video |
| `structure` | The parts of the script, each with its start time |
| `callToAction` | The call to action, or `null` |
| `strengths`, `improvements` | What works, and what to change |
| `speech` | Pace, hesitations, repeated tics (3 uses or more), long pauses (1.5 seconds or more) |
| `text` | The transcript, with hesitations kept |

### Use cases

- **Improve your own videos:** score drafts before posting and rework weak hooks.
- **Swipe file of hooks:** collect the openings of a niche's best-performing videos.
- **Competitor analysis:** compare structures, calls to action and pacing across creators.
- **UGC and ad review:** check creator videos before using them in campaigns.
- **Coaching:** give creators objective figures on pace and filler words.

### FAQ

#### How are filler words counted?

The transcript is made with an instruction to keep hesitations, then each "um", "uh", "euh", "äh" and similar is counted from the word list. Words such as "like", "so", "du coup" or "en fait" are reported as tics when used 3 times or more. Speech recognition can still miss some quick hesitations, so treat counts as a lower bound.

#### What does the AI see?

The timed transcript, the caption, the duration and the speech figures. It does not see the images, so on-screen text and visuals are not part of the analysis. The analysis is written by OpenAI's `gpt-6-luna`; `analysisIsAiGenerated` says so on every result.

#### Which links work?

Public TikTok videos, Instagram Reels and YouTube videos and Shorts (read by Google's Gemini model, with times to the second); Loom, Twitch, SoundCloud and direct audio or video files work too. You can also pick the dataset of a TikTok, Instagram or YouTube scraper run under **Or: links from another Actor's results**. Private or deleted posts cannot be read. Instagram sometimes refuses a download; that video is then reported as failed and not charged.

#### Can I get the feedback in my language?

Yes: set **Analysis language**. The transcript stays in the video's language.

### Limits

- Free Apify plan: 10 minutes of audio per run in total.
- The transcription service is shared; when it is busy, a video can fail with a message saying when to try again. It is then not charged.
- Videos with music only have no transcript and no analysis, and are not charged.

### Other Actors you may find useful

| Actor | What it does |
|---|---|
| [TikTok Transcript Generator](https://apify.com/spokentext/tiktok-transcript) | Transcripts of TikTok videos only, at the per-minute price |
| [Instagram Reels Transcript Generator](https://apify.com/spokentext/instagram-reel-transcript) | Transcripts of Instagram Reels only |
| [Podcast Summary](https://apify.com/spokentext/podcast-summary) | AI summaries, chapters and show notes for podcast episodes |

### Run it from the API

```python
from apify_client import ApifyClient

client = ApifyClient("YOUR_TOKEN")
run = client.actor("spokentext/tiktok-reels-script-analyzer").call(run_input={
    "urls": ["https://www.tiktok.com/@nasa/video/7700397098994273549"],
})
for video in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(video["score"], video["hookText"], video["improvements"][0])
```

This Actor is an independent tool. It is not affiliated with or endorsed by TikTok, Instagram, Meta, OpenAI or the creators it analyses; their names only describe the content it works with.

### Feedback

Something failed or gave a wrong result? Open an issue in the **Issues** tab of this page, with the error message from your results: every report is read and fixed. If the Actor saved you time, a rating helps others find it.

# Actor input Schema

## `urls` (type: `array`):

Public TikTok videos or Instagram Reels, one link per line: yours or your competitors'. Loom, Twitch and SoundCloud links and audio or video files work too. Public YouTube videos and Shorts work too. A creator's profile link (https://www.tiktok.com/@name) takes their latest videos.

## `maxVideosPerProfile` (type: `integer`):

For TikTok profile links (tiktok.com/@name): how many of the creator's latest videos to take, newest first. Ignored for single video links.

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

Skip videos this Actor already processed for your account in an earlier run: they are not charged again. Turn it on when you schedule a profile, so each run only pays for the creator's new videos.

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

Pick the dataset of a run of TikTok Scraper, Instagram Scraper or YouTube Scraper: every link in it is processed, as if pasted above. Useful to chain this Actor after a scraper.

## `datasetUrlField` (type: `string`):

The field that holds the links. Leave empty to detect it: url, postUrl, webVideoUrl, shareUrl, link, videoUrl...

## `datasetMaxItems` (type: `integer`):

Each link read is processed and charged as usual.

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

Two-letter language code of the audio (en, fr, es, de...). Leave empty to detect it automatically. Setting it improves accuracy on short or noisy audio.

## `analysisLanguage` (type: `string`):

The language of the feedback, such as English or French. Leave empty to use the video's language.

## `includeSegments` (type: `boolean`):

Add a list of timestamped segments (start, end, text) to each result.

## `maxMinutesPerFile` (type: `integer`):

Longer videos are cut at this length, so a single run can never cost more than you expect.

## Actor input object example

```json
{
  "urls": [
    "https://www.tiktok.com/@nasa/video/7700397098994273549",
    "https://www.instagram.com/reel/CqlKdduP1p-/"
  ],
  "maxVideosPerProfile": 10,
  "onlyNewVideos": false,
  "datasetMaxItems": 100,
  "includeSegments": false,
  "maxMinutesPerFile": 300
}
```

# Actor output Schema

## `transcripts` (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 = {
    "urls": [
        "https://www.tiktok.com/@nasa/video/7700397098994273549",
        "https://www.instagram.com/reel/CqlKdduP1p-/"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("spokentext/tiktok-reels-script-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 = { "urls": [
        "https://www.tiktok.com/@nasa/video/7700397098994273549",
        "https://www.instagram.com/reel/CqlKdduP1p-/",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("spokentext/tiktok-reels-script-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 '{
  "urls": [
    "https://www.tiktok.com/@nasa/video/7700397098994273549",
    "https://www.instagram.com/reel/CqlKdduP1p-/"
  ]
}' |
apify call spokentext/tiktok-reels-script-analyzer --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,spokentext/tiktok-reels-script-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/1f4kH9aoQu0rCg6Hx/builds/I9Gkhbi3LtyXdYIse/openapi.json
