# TikTok Transcript Scraper (`latentlark/tiktok-transcript`) Actor

Get TikTok video transcripts (text, timed segments, SRT) in the original spoken language, from video links or creator handles, plus views, likes and author data. Optional Whisper fallback.

- **URL**: https://apify.com/latentlark/tiktok-transcript.md
- **Developed by:** [LatentLark](https://apify.com/latentlark) (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

from $2.80 / 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.
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 Scraper: Video to Text, SRT & Captions

**Turn TikTok videos into clean text.** Paste video links or creator handles. For each video you get the **full transcript in the original spoken language**, timed segments, a ready-made **SRT** file, and the video's metadata (description, posting date, duration, hashtags, views, likes, author and follower count).

- 🗣️ **Original language, not a translation.** TikTok often lists an English machine translation first. This Actor picks the creator's own spoken-language captions (Spanish stays Spanish, Portuguese stays Portuguese). You can still ask for a translated track with `captionLanguage`.
- ⚡ **Fast and cheap.** It uses TikTok's own auto-captions: about 0.5–2 seconds per video, with no login, no TikTok account and no residential proxy.
- 🎙️ **Optional Whisper fallback** for videos without TikTok captions. It's off by default, so you never pay for it unless you turn it on.
- 👤 **Creators in, transcripts out.** Give a handle such as `@penniestopounds` and it transcribes their latest videos.
- 🟢 **Fail-safe runs.** Deleted, private and caption-less videos come back as **free status rows** with a `note`. The run still **SUCCEEDS**, so schedules and integrations stay green.
- 💸 **Pay per transcript:** $4 per 1,000 TikTok-caption transcripts. Rows without a transcript are free.

### Quick start (about 20 seconds)

1. Click **Try for free** (or **Start** in Console). The form is prefilled with:
   - two videos: an English career-advice clip and a Portuguese news clip;
   - the creator `@penniestopounds`, with **3 videos** per creator.
2. Click **Start**. In about 10–20 seconds you get **~5 transcripts** with text, SRT, language and video stats, for about **$0.03**.
3. Replace the links with your own videos or creators. Turn on **Whisper fallback** if you also need videos that have no TikTok captions.

### What people use it for

- **Content repurposing:** turn TikToks into blog posts, newsletters, X threads or YouTube Shorts scripts.
- **Subtitles:** download SRT files for re-editing, translation or accessibility.
- **AI and LLM pipelines:** feed transcripts to ChatGPT or Claude for summaries, hooks, topics and sentiment, or build RAG datasets.
- **Creator and competitor research:** what top creators in your niche actually *say*, which hooks they use, and which products they mention.
- **Brand and ad monitoring:** find mentions of your brand in spoken content, not just captions or hashtags.
- **Academic and media research:** quotable, timestamped text from short-form video.
- **Spreadsheets:** send results to Google Sheets with [Google Sheets Export](https://apify.com/latentlark/sheets-export).

### Input

| Field | What it does |
|---|---|
| `videoUrls` | TikTok video links (`https://www.tiktok.com/@user/video/…`), `vm.tiktok.com` / `vt.tiktok.com` short links, or bare video IDs |
| `profiles` | Creator handles or profile URLs (`@user`, `https://www.tiktok.com/@user`) |
| `maxVideosPerProfile` | Recent videos per creator (default 10; TikTok's public embed shows about the latest 10) |
| `captionLanguage` | Empty = original spoken language (recommended). `en`, `eng-US`, `es`… = prefer that translated track if TikTok has it |
| `includeSegments` / `includeSrt` / `includeVtt` | Timed segments (on), SRT (on), WebVTT (off) |
| `whisperFallback` | Off by default. Transcribe videos without TikTok captions with Whisper |
| `whisperModel` | `base` (built in, default), `small` (more accurate, slower) or `tiny` |
| `maxWhisperVideos` / `whisperMaxDurationSecs` | Safety caps for Whisper (default 20 videos, 300 s max length) |
| `proxyMode` | `auto` (default: direct first, Apify Proxy on retry), `none` or `datacenter` |
| `maxConcurrency` | Videos in parallel (default 8) |

**Example input:**

```json
{
  "videoUrls": [
    "https://www.tiktok.com/@careersbychris/video/7696221120462114062",
    "https://www.tiktok.com/@g1/video/7701696635159547154"
  ],
  "profiles": ["@penniestopounds"],
  "maxVideosPerProfile": 3
}
```

**Example with Whisper** (also transcribe videos without captions):

```json
{
  "profiles": ["@yourcompetitor"],
  "maxVideosPerProfile": 10,
  "whisperFallback": true,
  "maxWhisperVideos": 10
}
```

### Output

One row per video. A transcript row looks like this (SRT shortened):

```json
{
  "url": "https://www.tiktok.com/@duolingo/video/7698777733794483469",
  "videoId": "7698777733794483469",
  "status": "ok",
  "transcript": "Papoy llegó con flow y con crocs. No me mires las crocs, traigo pura aura en las crocs…",
  "language": "spa-ES",
  "transcriptSource": "tiktok_captions",
  "captionType": "original",
  "availableCaptions": [{"language": "eng-US", "type": "translation"}, {"language": "spa-ES", "type": "original"}],
  "segments": [{"start": 0.16, "end": 2.4, "text": "Papoy llegó con flow y con crocs."}],
  "srt": "1\n00:00:00,160 --> 00:00:02,400\nPapoy llegó con flow y con crocs.\n…",
  "description": "tengo TOO MUCH flow",
  "createTime": "2026-10-20T15:50:13Z",
  "durationSecs": 10,
  "hashtags": [],
  "author": {"handle": "duolingo", "nickname": "Duolingo", "verified": true, "followers": 18400000},
  "stats": {"plays": 1100000, "likes": 106800, "comments": 3669, "shares": 55700, "saves": 15864},
  "music": {"title": "sonido original", "author": "Pauchisss", "original": true},
  "fetchedVia": "direct",
  "attempts": 1
}
```

**`status` values**
| status | meaning | charged |
|---|---|---|
| `ok` | Transcript returned (`transcriptSource`: `tiktok_captions` or `whisper`) | ✅ |
| `no_captions` | TikTok has no captions for this video (often music-only or no speech). Metadata is still returned | Free |
| `unavailable` | Deleted, private or region-restricted (`tiktokStatusCode`, e.g. 10231) | Free |
| `photo_post` | Photo or slideshow post, nothing to transcribe | Free |
| `invalid_input` / `no_videos` / `error` | Bad link, empty creator, or TikTok kept blocking after 3 attempts | Free |

The **Overview** tab in the dataset shows a compact table. Export to JSON, CSV, Excel or Google Sheets.

### Pricing

Pay per event, with volume discounts on higher Apify plans:

| Event | What it is | Free plan | Bronze | Silver | Gold+ |
|---|---|---|---|---|---|
| `apify-actor-start` | Once per run (per GB of memory; the default 512 MB counts as one start) | $0.005 | $0.005 | $0.005 | $0.005 |
| `transcript` | One video transcript from TikTok's own captions | $0.004 | $0.0036 | $0.0032 | $0.0028 |
| `whisper-transcript` | One video transcript from the Whisper fallback (only when `whisperFallback` is on and speech is found) | $0.015 | $0.0135 | $0.012 | $0.0105 |

- **Free:** `no_captions`, `unavailable`, `photo_post`, `invalid_input`, `no_videos` and `error` rows, plus duplicates. Each video is charged at most once.
- **Examples (Free plan):**
  - The prefilled example (~5 transcripts): about **$0.03**.
  - 1,000 videos with ~65% captioned: about **$2.61**.
  - The same 1,000 videos with Whisper for the rest: about **$7.85**.
- Set **Max cost per run** in Console to cap spend. The Actor stops cleanly when it reaches the limit.

### How it works and limitations

- **Native captions first.** Most talking-head TikToks have TikTok auto-captions. In our tests, about **70% of creator talking-head videos** and about 50% of brand and news videos had them. Music-only clips, memes and some languages have none.
- **The Whisper fallback is optional.** The Actor downloads the video's audio and transcribes it on the Apify server with faster-whisper (base model built in). This takes a few seconds per short video. It's slower than native captions, which is reflected in the higher event price. The default 512 MB works for the built-in `base` model; use 1 GB for `small`.
- **Original vs translation.** `captionType: "original"` is the creator's spoken language. TikTok also offers machine translations for some videos; they're listed in `availableCaptions` and can be requested with `captionLanguage`.
- **Creators:** only the latest ~10 videos per creator are reachable through TikTok's public embed. For older videos, pass their URLs directly.
- **Accuracy** is that of TikTok's auto-captions (or Whisper). Names, brands and slang can be misspelled.
- **Blocks:** about 1–2% of requests get a TikTok challenge page. The Actor retries automatically with a new session through Apify Proxy (up to 3 attempts in total). Our 500-URL tests reached 98–99.7% success at 8 videos in parallel.
- Cover image and video URLs are signed TikTok CDN links that expire after some days.
- Public videos only. No login, no TikTok account, no private data.

### FAQ

**I got 0 transcripts. Why?**
Check the `status` and `note` (or `error`) field of each row:

- `no_captions` means TikTok has no captions for that video. Turn on `whisperFallback` to transcribe it anyway.
- `unavailable` means the video is deleted, private or region-locked.
- `invalid_input` means the link wasn't recognised. Use the full `https://www.tiktok.com/@user/video/<id>` link or a short `vm.tiktok.com` link.
- A creator row with `no_videos` means the account is private or has no public videos.

None of these rows are charged.

**Why is my transcript in Spanish (or another language) and not English?**
By default you get the language actually spoken in the video. If TikTok also has an English translation, set `captionLanguage` to `en`.

**Does it work for YouTube Shorts or Instagram Reels?**
No, this Actor is TikTok-only.

**Can I get more than ~10 videos from a creator?**
TikTok's public embed only lists the latest videos. Collect older video URLs elsewhere and pass them in `videoUrls`.

**Do I need a TikTok account, cookies or residential proxies?**
No.

**How do I get SRT files?**
Each `ok` row has an `srt` field. Export the dataset, or read the field through the API.

### More from LatentLark

- [Facebook Reels Scraper + Transcripts](https://apify.com/latentlark/facebook-reels-scraper): public Facebook Reels with plays, reactions, shares and a spoken-word transcript (captions or Whisper), no login.
- [TikTok Ads Library Scraper](https://apify.com/latentlark/tiktok-ads-library): competitors' TikTok ads from the EU Ad Library and Creative Center Top Ads.
- [Google Sheets Export & Import (No OAuth)](https://apify.com/latentlark/sheets-export): send any dataset to Google Sheets.
- [Telegram Channel Monitor](https://apify.com/latentlark/telegram-channel-monitor): posts from public Telegram channels.
- [Creator Commerce Competitor Finder](https://apify.com/latentlark/creator-commerce-competitor-finder): creators and brands on LTK and ShopMy.

# Actor input Schema

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

One link per line: https://www.tiktok.com/@user/video/123…, vm.tiktok.com / vt.tiktok.com short links, or bare video IDs. Duplicates are removed.

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

e.g. @penniestopounds or https://www.tiktok.com/@penniestopounds. Gets each creator's most recent videos (TikTok's public embed shows about the latest 10).

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

How many recent videos to transcribe per creator. TikTok's public embed exposes roughly the latest 10, so values above ~10 rarely add more.

## `captionLanguage` (type: `string`):

Leave empty (recommended) to get the original spoken-language transcript. Enter a language code such as 'en' or 'eng-US' to prefer TikTok's machine-translated caption track when it exists; otherwise the original is returned.

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

Add a segments array: \[{start, end, text}] in seconds.

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

Add an SRT subtitle string (ready for video editors and YouTube).

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

Add a WebVTT subtitle string.

## `whisperFallback` (type: `boolean`):

Off by default. When on, videos with no TikTok captions are downloaded and transcribed with Whisper (base model is built in). Charged as the higher-priced whisper-transcript event only when it returns speech. Slower than native captions; default 512 MB is fine for base, use 1 GB for small.

## `whisperModel` (type: `string`):

base (default, built in, fast) is good for clear speech. small is more accurate but slower and downloads at run start. tiny is fastest. Use 1 GB memory for small.

## `maxWhisperVideos` (type: `integer`):

Safety cap: at most this many Whisper transcriptions per run.

## `whisperMaxDurationSecs` (type: `integer`):

Skip Whisper for videos longer than this (seconds).

## `proxyMode` (type: `string`):

Auto (recommended): direct request first, then retries via Apify Proxy with a fresh session if TikTok challenges or rate-limits. Residential proxy is not needed.

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

Proxy used for retries. Apify datacenter proxy (default) is enough.

## `maxConcurrency` (type: `integer`):

Videos processed in parallel (1–16).

## Actor input object example

```json
{
  "videoUrls": [
    "https://www.tiktok.com/@careersbychris/video/7696221120462114062",
    "https://www.tiktok.com/@g1/video/7701696635159547154"
  ],
  "profiles": [
    "@penniestopounds"
  ],
  "maxVideosPerProfile": 3,
  "includeSegments": true,
  "includeSrt": true,
  "includeVtt": false,
  "whisperFallback": false,
  "whisperModel": "base",
  "maxWhisperVideos": 20,
  "whisperMaxDurationSecs": 300,
  "proxyMode": "auto",
  "proxyConfiguration": {
    "useApifyProxy": true
  },
  "maxConcurrency": 8
}
```

# Actor output Schema

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

No description

## `summary` (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/@careersbychris/video/7696221120462114062",
        "https://www.tiktok.com/@g1/video/7701696635159547154"
    ],
    "profiles": [
        "@penniestopounds"
    ],
    "maxVideosPerProfile": 3
};

// Run the Actor and wait for it to finish
const run = await client.actor("latentlark/tiktok-transcript").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/@careersbychris/video/7696221120462114062",
        "https://www.tiktok.com/@g1/video/7701696635159547154",
    ],
    "profiles": ["@penniestopounds"],
    "maxVideosPerProfile": 3,
}

# Run the Actor and wait for it to finish
run = client.actor("latentlark/tiktok-transcript").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/@careersbychris/video/7696221120462114062",
    "https://www.tiktok.com/@g1/video/7701696635159547154"
  ],
  "profiles": [
    "@penniestopounds"
  ],
  "maxVideosPerProfile": 3
}' |
apify call latentlark/tiktok-transcript --silent --output-dataset

```

## MCP server setup

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

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/gZPhBbXnIeGhNGJ2u/builds/uix9i6wKo1VTP7NUe/openapi.json