# TikTok Transcript & Hook Extractor: On-Screen Text & Structure (`juramoshkov/tiktok-script-extractor`) Actor

TikTok transcript plus what a transcript misses: the text written on the frames, the opening hook and its type, the beat-by-beat structure with timestamps and the call to action. Works on silent and music-only videos. Paste video URLs, get one row per video. No login.

- **URL**: https://apify.com/juramoshkov/tiktok-script-extractor.md
- **Developed by:** [Jura Moshkov](https://apify.com/juramoshkov) (community)
- **Categories:** Social media, AI, Videos
- **Features:** Limited permissions
- **Stats:** 3 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $30.00 / 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.
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

## TikTok Transcript & Hook Extractor: On-Screen Text & Structure

Get the TikTok transcript and everything a transcript misses. For each video you get the spoken words, the text written on the frames, the opening hook and its type, the beat-by-beat structure with timestamps, and the call to action. It watches the video and listens to it in one pass, so it also works on silent and music-only videos. No TikTok account, no cookies, no proxies.

- **Transcript**: everything said, verbatim, in the original language.
- **On-screen text**: titles, labels, list items and prices burned into the frames, with the second each one appears. Subtitles that only repeat the speech are left out.
- **Hook**: the exact opening line (or, for a wordless opening, what the first shot shows), when it ends, and what kind of hook it is.
- **Structure**: hook → context → proof → value → call to action, with start and end seconds.
- **Call to action**: the exact words and the type (follow, comment, link, buy...).
- **Stats**: plays, likes, comments, shares, saves and engagement rate.
- **Flat rows**: ready for CSV, Excel, Google Sheets or your LLM pipeline.

### What is a TikTok script extractor?

A transcript tells you what was said. It does not tell you that the first frame carried the title "3 wines under $20", that the hook ended at second 3, or that the video closed by asking for a comment. This actor returns the script of a TikTok the way a content strategist would write it down: words, on-screen text, hook, structure and call to action, one row per video.

Use it as a TikTok transcript scraper that also reads the frames, as a TikTok hook extractor for swipe files, or as a video-to-text step in front of an LLM.

### What you get per video

| Field | Example |
|---|---|
| Hook | "In one of the most star studded GTA radio lineups in its history" · `bold_claim` · ends at 3.8 s |
| Transcript | "In one of the most star studded GTA radio lineups in its history, Bad Bunny..." |
| On-screen text | "GTA 6 confirms Bad Bunny, Burna Boy and Lana Del Rey | COCOTEO FM | CHAMBER 106.6" |
| Structure | hook 0-3.8s → value 3.8-40.3s → proof 40.3-58.9s → cta 58.9-60.1s |
| Call to action | "What station are you gonna be listening to?" · `comment` |
| Format and topics | voiceover b-roll · GTA 6, Gaming, Music |
| Summary | one or two sentences |
| Creator, description, posting date, duration | `bbcnews`, 61 s, 2026-10-08 |
| Plays, likes, comments, shares, saves, engagement rate | 867400, 85200, 1445, 9109, 5490, 0.1167 |

#### Example output row

```json
{
  "videoUrl": "https://www.tiktok.com/@bbcnews/video/7694397093380853015",
  "hookText": "In one of the most star studded GTA radio lineups in its history",
  "hookType": "bold_claim",
  "hookEndSeconds": 3.8,
  "transcript": "In one of the most star studded GTA radio lineups in its history, Bad Bunny, Burner Boy, Lana Del Rey and Robin will host some of the newly revealed radio stations in GTA 6...",
  "transcriptSource": "tiktok_captions",
  "language": "eng-US",
  "wordCount": 194,
  "onScreenText": "GTA 6 confirms Bad Bunny, Burna Boy and Lana Del Rey | VOICE OF MEL RAMSAY BBC Journalist | COCOTEO FM | CHAMBER 106.6",
  "onScreenCards": [
    { "start": 0, "text": "GTA 6 confirms Bad Bunny, Burna Boy and Lana Del Rey" },
    { "start": 14, "text": "COCOTEO FM" }
  ],
  "hasBurnedInCaptions": true,
  "structureOutline": "hook 0-3.8s → value 3.8-40.3s → proof 40.3-58.9s → cta 58.9-60.1s",
  "structure": [
    { "beat": "hook", "start": 0, "end": 3.8, "summary": "The video introduces the star-studded radio lineups in GTA 6." },
    { "beat": "value", "start": 3.8, "end": 40.3, "summary": "Detailed overview of specific hosts and radio stations confirmed for the game." },
    { "beat": "proof", "start": 40.3, "end": 58.9, "summary": "Teasers of featured songs and the new gameplay mechanic of listening on foot." },
    { "beat": "cta", "start": 58.9, "end": 60.1, "summary": "A question to the viewer about their preferred station." }
  ],
  "ctaText": "What station are you gonna be listening to?",
  "ctaType": "comment",
  "format": "voiceover b-roll",
  "topics": ["GTA 6", "Gaming", "Music"],
  "summary": "This video details the newly revealed radio stations, celebrity hosts, and upcoming features in GTA 6.",
  "authorUsername": "bbcnews",
  "durationSeconds": 61,
  "postedAt": "2026-10-08T20:30:08.000Z",
  "plays": 867400,
  "likes": 85200,
  "comments": 1445,
  "shares": 9109,
  "saves": 5490,
  "engagementRate": 0.1167
}
```

### How much does it cost?

Pay per result: $0.04 per analyzed video on the Apify Free plan, $0.036 on Bronze, $0.033 on Silver and **$0.03 on Gold and above**. That is **$30-40 per 1,000 videos**. One flat price per video: no per-minute meter, no separate charge for the transcript.

You pay only for videos that come back analyzed. A private or removed video, a photo or slideshow post, a video that is too long, or a link that is not a TikTok video costs nothing. The same video pasted twice is billed once. Set **Max spend** and the run stops on its own before it bills past it.

The Free plan analyzes up to 5 videos per run. Paid plans have no cap.

Only need the words? The [TikTok Transcript Scraper](https://apify.com/juramoshkov/tiktok-transcript-scraper) returns the transcript alone for $6-10 per 1,000 videos.

### How to use it

1. Paste one or more TikTok video URLs, e.g. `https://www.tiktok.com/@bbcnews/video/7694397093380853015`. Short share links work too.
2. Run. A video takes about 10 seconds; two are analyzed side by side.
3. Export as JSON, CSV or Excel, or pull it over the API.

### How do I use it with an AI agent (MCP)?

This actor is available as a tool through the [Apify MCP server](https://mcp.apify.com/). An agent can call it with a plain input filled straight from the schema:

```json
{"videoUrls": ["https://www.tiktok.com/@bbcnews/video/7694397093380853015"]}
```

The output is one flat JSON object per video, with nothing to unwrap before handing it to a model.

### Common use cases

- **Hook swipe files**: collect the opening lines of high-performing videos, with their type and length.
- **Script writing**: reverse-engineer how a format is built (how long the hook runs, where the proof sits, when the ask comes) and write to that outline.
- **Silent and text-only videos**: recipes, checklists, price lists and tutorials where the content is on the frames, not in the audio.
- **UGC and ad creative research**: see what is actually said and shown, and what the viewer is asked to do.
- **Competitor and niche research**: break down the top videos of a niche into rows you can sort and filter.
- **Content repurposing**: turn a TikTok into a blog post, newsletter or thread with the on-screen points included.
- **AI and LLM pipelines**: feed structured video content into summarizers, classifiers and RAG.

### Is it legal?

It reads publicly available videos: what anyone sees in the TikTok player without logging in. It does not log in anywhere or use your accounts. The words and images in a video belong to its creator; you are responsible for how you use the output.

### FAQ

#### How do I get the transcript of a TikTok video?

Paste the video URL and run. The full text is in the `transcript` field. When TikTok has captions for the video they are used word for word; otherwise the audio is transcribed.

#### How is this different from a TikTok transcript scraper?

A transcript scraper returns the spoken words. This actor also reads the frames and returns the on-screen text, the hook, the structure and the call to action, so a video with no speech still comes back with its content.

#### Does it work on videos with no speech?

Yes. A music-only or silent video comes back with its on-screen text, hook, structure and summary; the `transcript` field is empty and `transcriptSource` is `none`. When the opening has no words at all, `hookType` is `visual` and `hookText` describes the opening shot.

#### What are the hook types?

`question`, `bold_claim`, `curiosity_gap`, `story`, `problem`, `result_first`, `list`, `news`, `visual` and `other`. The label is a fixed set so you can filter and count across videos.

#### Are the burned-in subtitles included in the on-screen text?

No. Subtitles that repeat the speech are left out, so `onScreenText` holds only the text the creator designed into the video. `hasBurnedInCaptions` tells you whether the video had such subtitles.

#### Which languages are supported?

Any language. The transcript and on-screen text stay in the original language; the summary, format and topics are in English.

#### How long can a video be?

Up to about 4 minutes. A longer video comes back as a free row that says so.

#### Do I need a TikTok account, cookies or proxies?

No. There is nothing to log into and no proxy to configure.

#### Can I analyze every video of a profile or a hashtag?

This actor takes video URLs. Collect the URLs with any TikTok profile or hashtag scraper and paste them here.

#### Why does a video come back without a breakdown?

It is private, removed, region-locked, a photo post, or longer than the limit. The row says which, and it is not billed.

# Actor input Schema

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

One TikTok video link per line, e.g. https://www.tiktok.com/@user/video/1234567890. Short share links (vm.tiktok.com) work too. The same video pasted twice is analyzed and billed once. Videos up to about 4 minutes; photo and slideshow posts come back as a free row. A run with no input analyzes the example.

## `maxBudgetUsd` (type: `integer`):

Hard ceiling on what this run can charge. It is turned into a video count before the first video, so the run stops on its own rather than billing past it. Set 0 for no ceiling.

## Actor input object example

```json
{
  "videoUrls": [
    "https://www.tiktok.com/@bbcnews/video/7694397093380853015"
  ],
  "maxBudgetUsd": 5
}
```

# Actor output Schema

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

No description

## `resultsCsv` (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 = {
    "videoUrls": [
        "https://www.tiktok.com/@bbcnews/video/7694397093380853015"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("juramoshkov/tiktok-script-extractor").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/@bbcnews/video/7694397093380853015"] }

# Run the Actor and wait for it to finish
run = client.actor("juramoshkov/tiktok-script-extractor").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/@bbcnews/video/7694397093380853015"
  ]
}' |
apify call juramoshkov/tiktok-script-extractor --silent --output-dataset

```

## MCP server setup

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

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/LRWkv6aLHUmIRUT17/builds/AdlMeW1qaXRF5qdcm/openapi.json
