# TikTok Transcript Scraper: videos, profiles, hashtags & search (`pikoulas/tiktok-transcripts`) Actor

Get the transcript of TikTok videos as text, timestamped segments or SRT/VTT subtitles, from video URLs, whole profiles, hashtags or search: the captions TikTok has, in any language, and Whisper speech-to-text for videos without. With each video's hook, views, likes, date and author. No login.

- **URL**: https://apify.com/pikoulas/tiktok-transcripts.md
- **Developed by:** [Spyridon Pikoulas](https://apify.com/pikoulas) (community)
- **Categories:** Social media, Videos, AI
- **Features:** Limited permissions
- **Stats:** 6 total users, 4 monthly users, 95.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1.00 / 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 Transcript Scraper

Get the transcript of TikTok videos as clean text, timestamped segments, or SRT and WebVTT
subtitle files, from four kinds of source, without an account or a browser:

- **Videos:** by URL, vm.tiktok.com or vt.tiktok.com short link, or ID.
- **Profiles:** a creator's videos, newest first, as far back as the profile goes, by username,
  @handle or URL.
- **Hashtags:** the videos TikTok shows for a hashtag.
- **Search:** the videos TikTok shows for a keyword, in its order.

Every result also carries the video's caption, date, duration, views, likes, comments, shares and
saves, hashtags, sound, cover, and its author's username, name, verified badge and followers, the
list of caption languages the video has, and its `hook`: what is said in its first 5 seconds.

It is fast: 300 videos from two profiles, a hashtag and a search, 184 of them with a transcript,
took 28 seconds. It costs **$1 per 1,000 transcripts**, on every Apify plan, the free one too, and videos
without captions are free.

For the videos TikTok has no captions for, turn on **Speech-to-text**: OpenAI's Whisper, open
source, run inside the actor on Apify's servers, transcribes what is said, in the language spoken.
Nothing is sent to an outside AI service. Those transcripts cost **$0.003 per started minute** of
video, $0.008 with the more accurate Whisper small.

### What people use it for

- **AI and LLM pipelines:** summaries, RAG over a creator's videos, training data.
- **Content research:** what's said in a niche, a hashtag or a search, as text you can search.
- **Repurposing:** turn videos into posts, newsletters, scripts or subtitles.
- **Brand and trend monitoring:** what creators say about a product, day by day.

### How to scrape TikTok transcripts

1. Click **Try for free**; Apify's free plan covers a first run.
2. Fill in any of **Videos**, **Profiles**, **Hashtags** and **Search terms**, and how many videos
   you want from each.
3. Click **Start**, then download the results as JSON, CSV, Excel or HTML, or read them through
   the API.

Turn on **Skip videos without a transcript** to get transcripts only; the counts then count
transcripts. **Speech-to-text** fills in the videos without captions, with Whisper base, fast and
good on clear speech, or Whisper small, more accurate on accents, noise, names and languages other
than English, and about three times slower; runs get 4 GB of memory with it on. **Preferred languages** picks among a video's tracks: most videos have one, in the
language spoken, and some have the creator's own captions or English translations too. Turn on
**Include timestamps** for `segments`, each line with its start and end, and **Include SRT** or
**Include WebVTT** for a subtitle file, speech-to-text transcripts included.

To follow creators, schedule a run with **Only new videos from profiles** on: each run gives only
what the profiles posted since the last one, plus any video a run couldn't finish, so nothing is
paid for twice. The first run takes the latest videos as usual.

```json
{
  "profiles": ["garyvee", "https://www.tiktok.com/@nasa"],
  "maxVideosPerProfile": 100,
  "hashtags": ["sourdough"],
  "searchTerms": ["how to start a business"],
  "maxVideosPerSearch": 50,
  "publishedAfter": "2026-09-01",
  "skipVideosWithoutTranscript": true,
  "speechToText": true,
  "languages": ["en"],
  "includeTimestamps": true,
  "includeSrt": true
}
```

A TikTok URL works in any of the lists: a video URL pasted under profiles is read as a video.

### Output

```json
{
  "id": "7689547576265149710",
  "url": "https://www.tiktok.com/@nasa/video/7689547576265149710",
  "description": "There's plenty happening across NASA as September comes to a close! … Here's your NASA Minute!",
  "createdAt": "2026-09-25T18:52:22Z",
  "durationSeconds": 121,
  "views": 256800,
  "likes": 6898,
  "comments": 264,
  "shares": 127,
  "saves": 463,
  "hashtags": [],
  "authorUsername": "nasa",
  "authorName": "NASA",
  "authorVerified": true,
  "authorFollowers": 2200000,
  "musicTitle": "original sound - NASA",
  "coverUrl": "https://p16-common-sign.tiktokcdn-eu.com/tos-useast5-p-0068-tx/oo81DLfDSQmtRDqEWhfgltFstBcAGEJ3FCtLQg~tplv-tiktokx-origin.image?...",
  "isSlideshow": false,
  "input": "https://www.tiktok.com/@nasa/video/7689547576265149710",
  "availableLanguages": [{"code": "en", "autoGenerated": true, "translated": false}],
  "language": "en",
  "isAutoGenerated": true,
  "isTranslation": false,
  "transcriptSource": "captions",
  "hook": "This week, NASA inspired future explorers,",
  "text": "This week, NASA inspired future explorers, prepared the next crew for launch, studied life at the extremes, and looked ahead to the future of flight. Here's what's new and you're in NASA minute. …",
  "segments": [{"start": 0.42, "end": 2.94, "text": "This week, NASA inspired future explorers,"}],
  "srt": "1
00:00:00,420 --> 00:00:02,940
This week, NASA inspired future explorers,
…"
}
```

A video transcribed by speech-to-text has `"transcriptSource": "speech-to-text"` and its
`billedMinutes`. A video without a transcript comes with its details and a `noTranscriptReason`,
and costs nothing.

### Use it as an API

One call runs it and returns the results as JSON (for runs under 5 minutes; longer ones start a
run and read its dataset). Apify's Python and JavaScript clients, and its Make, Zapier and n8n
integrations, work the same way.

```bash
curl -X POST "https://api.apify.com/v2/acts/pikoulas~tiktok-transcripts/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"videos": ["https://www.tiktok.com/@nasa/video/7689547576265149710"], "profiles": ["nasa"], "maxVideosPerProfile": 3, "searchTerms": ["sourdough bread"], "maxVideosPerSearch": 3}'
```

Examples in Python and JavaScript, LangChain included, and a how-to guide for each source:
[transcripts-for-ai on GitHub](https://github.com/Spyridon-Pikoulas/transcripts-for-ai).

### Use it with AI agents

Claude, ChatGPT, Cursor and any other MCP client can call it as a tool through Apify's MCP server.
Add the server with your Apify token:

```json
{
  "mcpServers": {
    "transcripts": {
      "url": "https://mcp.apify.com?tools=pikoulas/tiktok-transcripts",
      "headers": {"Authorization": "Bearer YOUR_APIFY_TOKEN"}
    }
  }
}
```

Then ask in plain words, for example: "Get the transcripts of @nasa's last 5 TikToks and tell me what each one announces." To give the agent every transcript Actor at once
(YouTube, TikTok, Instagram, podcasts, any URL), use `?tools=pikoulas/youtube-transcripts,pikoulas/tiktok-transcripts,pikoulas/instagram-transcripts,pikoulas/podcast-transcripts,pikoulas/video-transcriber`.

### How much does it cost to scrape TikTok transcripts?

You pay **$0.001 per transcript**, which is $1 per 1,000, on every plan. Videos without captions are free, unless you turn on speech-to-text: then each started
minute of a video it transcribes is $0.003 with Whisper base and $0.008 with Whisper small, most videos being under a minute, and videos with nothing said stay
free. Traffic through Apify's residential proxy is paid as
well, at $0.0012 per 100 KB. Searches and hashtags always go through it, since TikTok cuts them
short from Apify's own IPs, and the rest of a run goes through it only when TikTok refuses those
IPs. A transcript from a search or hashtag takes about 15 KB, so about $0.0002 on top. There are
no monthly fees.

### Good to know

- Transcripts are the captions TikTok has: its own speech recognition, or the creator's. A
  video TikTok made no captions for (no speech, music only, or the creator turned captions off)
  has none unless speech-to-text is on. In our runs about half the videos of a search or hashtag
  had captions, and most of a talking creator's.
- Whisper writes what it hears: names, slang and words drowned in music can come out wrong, and
  Whisper small gets more of them right. Text on screen isn't read, only speech, and sung lyrics count as speech. A run at
  4 GB transcribes several minutes of video a minute with Whisper base, and about a third as
  much with Whisper small; more memory is faster, at the same price per minute.
- Logged out, TikTok shows a few hundred videos per hashtag (150 to 360 in our runs) and about
  270 per search. A profile's videos have no such limit.
- TikTok rounds views, likes and shares over 10,000 to three figures (942.2K), and the author's
  followers.
- A video found under several profiles, hashtags or searches is given once per run.
- Only new videos remembers each profile in your account's `tiktok-transcripts-memory` key-value
  store; delete it to start over. Set **Max videos per profile** above what a profile posts
  between runs: the older ones past it are passed over, as are those a run's spending limit stops
  short of.
- Private accounts and deleted or private videos can't be read; the log names them.

### FAQ

#### Is it legal to scrape TikTok?

It collects only what TikTok shows publicly, without logging in. [TikTok's terms](https://www.tiktok.com/legal/page/us/terms-of-service/en) prohibit this, and your use of it is your own responsibility. Personal data is also protected by laws such as the GDPR and the CCPA. If you're unsure, ask a lawyer;
Apify's [Is web scraping legal?](https://blog.apify.com/is-web-scraping-legal/) is a good start.

#### Something missing or not working?

Open an issue on the **Issues** tab with the input you used, or ask there for a field you need.

If it does what you need, a review on the **Reviews** tab helps others find it.

#### Transcripts from other sites?

[YouTube](https://apify.com/pikoulas/youtube-transcripts), [Instagram Reels](https://apify.com/pikoulas/instagram-transcripts), [podcasts (Apple Podcasts and RSS)](https://apify.com/pikoulas/podcast-transcripts) and [any other video or audio URL](https://apify.com/pikoulas/video-transcriber) each have an Actor of their own.

# Actor input Schema

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

Video URLs (tiktok.com/@user/video/...), vm.tiktok.com and vt.tiktok.com short links, or video IDs.

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

Usernames, @handles or profile URLs (tiktok.com/@nasa). Takes the profile's videos, newest first, as far back as it goes.

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

Videos from each profile, newest first.

## `hashtags` (type: `array`):

Hashtags, with or without the #, or hashtag URLs (tiktok.com/tag/cooking).

## `maxVideosPerHashtag` (type: `integer`):

TikTok shows a few hundred videos per hashtag to visitors who aren't logged in.

## `searchTerms` (type: `array`):

Keywords searched on TikTok, videos in TikTok's order.

## `maxVideosPerSearch` (type: `integer`):

TikTok shows about 270 videos per search to visitors who aren't logged in.

## `publishedAfter` (type: `string`):

Only videos posted on or after this date (YYYY-MM-DD). A profile's videos stop once they get past it.

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

For a scheduled run: each profile gives only the videos posted since the last run with this on, and those a run couldn't finish. The first run takes the latest ones as usual. Kept per profile in your account's key-value store tiktok-transcripts-memory; delete it to start over. Set the max videos per profile above what a profile posts between runs.

## `skipVideosWithoutTranscript` (type: `boolean`):

Leaves out the videos without a transcript (no captions, or with speech-to-text on, nothing said), so the counts above count transcripts. Otherwise they come with their details and the reason, free.

## `speechToText` (type: `boolean`):

Transcribes the videos TikTok has no captions for (about half of a search's or hashtag's) with OpenAI's Whisper, run inside the actor, in the language spoken. Charged per started minute of the video: $0.003 with Whisper base, $0.008 with Whisper small (twice on Apify's free plan); videos with nothing said stay free. Runs get 4 GB of memory with it on.

## `speechModel` (type: `string`):

Whisper base is fast and good on clear speech. Whisper small is more accurate on accents, noise, names and languages other than English, and takes about three times as long.

## `languages` (type: `array`):

Language codes in order of preference: en, es, de... Most videos have one track, in the language spoken; some have the creator's own captions or translations too. Empty, or none of these there: the video's own.

## `includeTimestamps` (type: `boolean`):

Adds the transcript as segments with their start and end in seconds, next to the plain text.

## `includeVtt` (type: `boolean`):

Adds the transcript as a WebVTT subtitle file.

## `includeSrt` (type: `boolean`):

Adds the transcript as an SRT subtitle file, ready for video editors.

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

Not needed for most runs. When TikTok refuses the run's IP on Apify, the run switches to Apify's residential proxy by itself.

## Actor input object example

```json
{
  "videos": [
    "https://www.tiktok.com/@nasa/video/7689547576265149710"
  ],
  "maxVideosPerProfile": 20,
  "maxVideosPerHashtag": 20,
  "maxVideosPerSearch": 20,
  "onlyNewVideos": false,
  "skipVideosWithoutTranscript": false,
  "speechToText": false,
  "speechModel": "base",
  "languages": [],
  "includeTimestamps": false,
  "includeVtt": false,
  "includeSrt": false,
  "proxyConfiguration": {
    "useApifyProxy": false
  }
}
```

# Actor output Schema

## `overview` (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 = {
    "videos": [
        "https://www.tiktok.com/@nasa/video/7689547576265149710"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("pikoulas/tiktok-transcripts").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/@nasa/video/7689547576265149710"] }

# Run the Actor and wait for it to finish
run = client.actor("pikoulas/tiktok-transcripts").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/@nasa/video/7689547576265149710"
  ]
}' |
apify call pikoulas/tiktok-transcripts --silent --output-dataset

```

## MCP server setup

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

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/kZNM79UA7tivQr5ju/builds/DlvdfpIAq8UvBeNip/openapi.json
