# TikTok Transcripts: Video Captions to Text & Hooks (`precious_bathmat/tiktok-transcript-scraper`) Actor

Get transcripts of TikTok videos from TikTok's own captions: full text, timed segments, language, words per minute and the opening hook, with plays, likes and caption. Paste video links or usernames. No login, no audio download.

- **URL**: https://apify.com/precious_bathmat/tiktok-transcript-scraper.md
- **Developed by:** [Mariam Ahmed](https://apify.com/precious_bathmat) (community)
- **Categories:** Social media, AI
- **Features:** Limited permissions
- **Stats:** 3 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$2.00 / 1,000 transcripts

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

## TikTok Transcripts: Video Captions to Text & Hooks

Get **transcripts of TikTok videos** as plain text and as timed lines, straight from **TikTok's own captions**, with no login, no API key and no audio download. Paste video links, or **usernames** to transcribe a creator's latest videos:

- **Full transcript** of what is said in the video, plus **timed segments** (start and end second of every line)
- **Language**, whether the captions are **auto-generated or added by the creator**, and the other caption languages TikTok offers (translated captions can be picked)
- **Word count, words per minute, when speech starts** and the **hook**: the first sentence of the video
- **Video stats**: plays, likes, comments, shares, saves, caption, hashtags, duration and posting date
- **All transcripts in one text file**, ready to paste into ChatGPT, Claude or a document

### What does this TikTok transcript scraper do?

```
@hubermanlab · 10 latest videos · 10 transcripts
 "What we self medicate when we self medicate is the pain of disconnection."
 Median 158 words per video · 205 words per minute · English (auto-generated)
```

1. Paste **TikTok video links** (or short `vm.tiktok.com` links, or video ids), and/or **usernames**.
2. Keep the **original language**, or ask for a translated one ("en", "es" ...) when TikTok has it.
3. You get **one row per video** with its transcript, plus **CSV** and **text** exports of every transcript.

```mermaid
flowchart LR
    A[Video links<br/>or usernames] --> B[Creator embed<br/>latest videos]
    A --> C[Video page<br/>stats, caption,<br/>caption tracks]
    B --> C
    C --> D[TikTok captions<br/>WebVTT]
    D --> E[Transcript<br/>text, timed lines,<br/>words per minute,<br/>hook]
```

### Who is it for?

- **Content creators and agencies**: study the hooks and scripts of videos that work, and repurpose your own videos into posts, threads and blogs
- **Marketers and brand teams**: what competitors and influencers actually say about products, word for word
- **Researchers, journalists and fact-checkers**: searchable text of what was said, with timestamps to quote
- **AI and automation builders**: clean video text for summaries, classification, RAG and content pipelines
- **Agencies running UGC and ads**: transcripts of ad creatives and sponsored videos for briefs and reviews

### What data do you get?

**Transcripts** (dataset, one row per video)

| Field | What it tells you |
|---|---|
| `transcript` | The full text of what is said |
| `segments` | Every caption line with `start` and `end` in seconds (optional) |
| `timestampedTranscript` | The text with `[0:07]` before each line (optional) |
| `transcriptLanguage`, `transcriptAutoGenerated`, `transcriptIsOriginalLanguage`, `availableLanguages` | Which captions were used and what else TikTok offers |
| `wordCount`, `wordsPerMinute`, `speechStartsAtSeconds`, `hook` | How dense the video is and how it opens |
| `plays`, `likes`, `comments`, `shares`, `saves` | The video's numbers |
| `caption`, `hashtags`, `soundTitle`, `durationSeconds`, `createdAt` | About the video |
| `author`, `authorNickname`, `url`, `videoId`, `source` | Whose video it is and how it was found |
| `hasTranscript`, `noTranscriptReason` | Videos with no captions are saved free, with the reason |

**Exports**: `TRANSCRIPTS_CSV` (every video in one sheet) and `TRANSCRIPTS_TXT` (every transcript in one text file, with links and captions).

### Example: 20 October 2026

8 profiles and 2 video links: **79 videos, 64 transcripts in 122 seconds**, 157 requests.

| Profile | Videos | With transcript | Median words | Words per minute | Language |
|---|---|---|---|---|---|
| @hubermanlab | 10 | 10 | 158 | 205 | English |
| @garyvee | 12 | 12 | 134 | 195 | English |
| @bbcnews | 10 | 10 | 190 | 182 | English |
| @gordonramsayofficial | 12 | 11 | 149 | 129 | English |
| @luisitocomunica | 12 | 9 | 214 | 185 | Spanish (English offered on 7) |
| @duolingo | 11 | 6 | 25 | 99 | English, Spanish, Japanese, Korean |
| @mrbeast | 10 | 5 | 21 | 209 | English |

- Videos with talking get a transcript almost every time; music-only and skit videos often have none (half of MrBeast's latest).
- Gary Vee opens with the line itself ("If you're 36, you're a fucking child."), Huberman with a question or a claim ("Do you ever recommend people memorize speeches?").

### Pricing

**$0.002 per transcript.** Videos without captions are saved **free**.

- 100 transcripts: **$0.20**
- A creator's latest videos (10 to 13): about **$0.02 to $0.03**
- The run above (64 transcripts): **$0.13**

### Good to know

- **Source**: these are TikTok's own captions, made by its speech recognition (or added by the creator). Nothing is downloaded or sent to a speech-to-text service, so it is fast and cheap.
- **Coverage**: most spoken videos in common languages have captions. Music-only videos, photo posts, some languages, and videos where the creator turned captions off have none; they are saved with `hasTranscript: false`.
- **Accuracy**: auto-generated captions can mishear names, brands and slang, and spoken words are not censored.
- **Profiles** give their **latest 10 to 13 videos** (pinned ones included), as TikTok's creator embed lists them. For more videos of an account, get the links with the [TikTok Profile & Video Scraper](https://apify.com/precious_bathmat/tiktok-profile-video-scraper) and paste them here.
- **Translated captions**: set **Language** to a code like `en` or `es`; when TikTok has no such track, the original is saved and the run summary says so.
- Data comes from **TikTok's public video pages**. **Not affiliated with TikTok.**

### Input

| Field | Meaning |
|---|---|
| **TikTok videos** | Video links, short links or video ids, one per line |
| **Profiles** | Usernames or profile links; each gives its latest videos |
| **Language** | `original` (default) or a language code for translated captions |
| **Timed segments** | On by default |
| **Timestamped text** | Off by default |
| **Save videos without a transcript** | On by default (free rows) |

### Integrations

Export to JSON, CSV, Excel or Google Sheets, or connect through the Apify API, webhooks, Make, Zapier and n8n. Send the text to an AI step to **summarise videos, pull out product mentions or turn videos into posts**, or **schedule it weekly** on the creators you follow. To read what viewers say under the same videos, use the [TikTok Comments Scraper](https://apify.com/precious_bathmat/tiktok-comments-scraper).

### Related tools

Other tools from the same publisher that pair well with this one:

- [X (Twitter) Profile Tracker: Followers & Latest Posts](https://apify.com/precious_bathmat/x-twitter-scraper)
- [Pinterest Pin & Profile Analytics: Saves, Boards & Links](https://apify.com/precious_bathmat/pinterest-scraper)
- [Snapchat Creator Stats: Subscribers, Stories & Spotlight](https://apify.com/precious_bathmat/snapchat-profile-scraper)
- [Twitch Analytics: Streamer Stats & Best Games to Stream](https://apify.com/precious_bathmat/twitch-channel-game-analytics)

# Actor input Schema

## `videos` (type: `array`):

Video links (https://www.tiktok.com/@user/video/123..., short vm.tiktok.com links) or video ids, one per line.

## `profiles` (type: `array`):

Optional usernames or profile links ("@hubermanlab", "https://www.tiktok.com/@garyvee"): transcripts of each profile's latest 10 to 13 videos.

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

"original" (default) for the language spoken in the video, or a language code such as "en" or "es" to take TikTok's translated captions when it has them (otherwise the original is saved).

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

Add every caption line with its start and end time in seconds.

## `includeTimestampedText` (type: `boolean`):

Add the transcript as text with a \[0:07] time before each line.

## `saveVideosWithoutTranscript` (type: `boolean`):

Also save videos TikTok has no captions for (music only, photo posts), with the reason. These rows are free.

## Actor input object example

```json
{
  "videos": [
    "https://www.tiktok.com/@garyvee/video/7528533857688243511"
  ],
  "language": "original",
  "includeSegments": true,
  "includeTimestampedText": false,
  "saveVideosWithoutTranscript": true
}
```

# Actor output Schema

## `transcripts` (type: `string`):

One row per video: transcript, language, word count, words per minute, hook, timed segments, plus plays, likes, comments, shares, caption and hashtags.

## `csv` (type: `string`):

Every video in one CSV, without the timed segments.

## `text` (type: `string`):

Every transcript in one plain-text file, ready to paste into an AI tool or a document.

## `summary` (type: `string`):

Requests, problems and the limits of the data.

# 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 = {
    "videos": [
        "https://www.tiktok.com/@garyvee/video/7528533857688243511"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("precious_bathmat/tiktok-transcript-scraper").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 = { "videos": ["https://www.tiktok.com/@garyvee/video/7528533857688243511"] }

# Run the Actor and wait for it to finish
run = client.actor("precious_bathmat/tiktok-transcript-scraper").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 '{
  "videos": [
    "https://www.tiktok.com/@garyvee/video/7528533857688243511"
  ]
}' |
apify call precious_bathmat/tiktok-transcript-scraper --silent --output-dataset

```

## MCP server setup

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

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/9e0EraCp5Q1MRMAqu/builds/u1532D9csAyS44PI8/openapi.json
