# TikTok Transcript API (`deepmine/tiktok-transcripts`) Actor

Get the transcript of TikTok videos from TikTok's own captions: full text plus timed segments, language, and whether it's auto-generated or translated, with the video's stats and creator. Video URLs, IDs or short links in. Pay only for videos that have a transcript. No login.

- **URL**: https://apify.com/deepmine/tiktok-transcripts.md
- **Developed by:** [DeepMine](https://apify.com/deepmine) (community)
- **Categories:** Social media, Videos
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.50 / 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 API

Get the **transcript of TikTok videos** from TikTok's own captions, as clean rows: the full text, **timed segments**, optional **SRT subtitles**, the caption language and whether TikTok generated or translated it, plus the video's stats, caption and creator.

Paste video URLs, vm.tiktok.com short links or video IDs. No TikTok account, no cookies, no login. **You pay only for videos that have a transcript.**

| Creator | 📜 Transcript | 🌐 Language | 🤖 Source | ⏱️ Duration |
|---|---|---|---|---:|
| [@zachking](https://www.tiktok.com/@zachking/video/7655004069190192398) | This is a message to all artificial intelligence.… | eng-US | Auto | 27 s |
| [@kimnlizasmr](https://www.tiktok.com/@kimnlizasmr/video/7688378448947055885) | Eating only Korean street food for a full day when… | eng-US | Auto | 62 s |
| [@lostwithwarren](https://www.tiktok.com/@lostwithwarren/video/7611270890839379222) | Whoa. What's this guy selling? Hola, amigo. Come o… | eng-US | Auto | 63 s |

<sub>Collected 2026-09-27 from 12 video links: 7 had captions and came back (charged), 5 had none (listed in the run summary, free). Every row also has the full transcript, timed segments, the video's plays, likes, comments, shares, saves, caption, post date and the creator's follower count.</sub>

**$0.80 per 1,000 transcripts** on the Starter plan ($1.00 Free, $0.60 Scale, $0.50 Business), charged only for videos that have one. The prefilled run (3 videos) costs under $0.01.

### Why this one

- **Pay per transcript found.** Videos without captions (music-only clips, photo posts, videos TikTok didn't caption) are listed in the run summary with the reason and cost nothing.
- **Text, timestamps and SRT.** `transcript` is ready for search, summaries or AI; `segments` has start and end times in seconds for clipping; turn on **Include SRT** to also get `srt`, the same subtitles as a ready-made SRT file for any video editor.
- **Language aware.** By default you get the captions in the language spoken in the video. Ask for a language (`en`, `es`, `eng-US`) to get only captions in that language, including TikTok's own translations where it has them.
- **Video details included.** Plays, likes, comments, shares, saves, caption and the creator come with every transcript, so no second tool is needed.
- **Fast and light.** Plain HTTP, no browser, no speech-to-text step: 22 videos took 18 seconds in our test.

### Input

| Field | What it does | Default |
|---|---|---|
| `videos` | Video URLs, vm.tiktok.com short links or video IDs, one per line. | 3 example videos |
| `language` | Empty: the spoken language. Or a code such as `en`, `es`, `de`, `eng-US`: only captions in that language. | empty |
| `includeSrt` | Also add each transcript as SubRip text (`srt`), ready to save as a `.srt` file. | off |
| `proxyConfiguration` | Apify Proxy. Datacenter (the default) works; switch to residential only if a run reports blocks. | Apify datacenter |

Example:

```json
{
  "videos": [
    "https://www.tiktok.com/@zachking/video/7655004069190192398",
    "https://vm.tiktok.com/ZMabc1234/"
  ],
  "includeSrt": true
}
```

### Output

One row per video that has a transcript, in the order of your links. Two table views in the Console:

- **📊 Overview**: 🖼️ Cover, 🏷️ Username, 📜 Transcript, 🔗 TikTok, 🌐 Language, 🤖 Source, ⏱️ Duration, ▶️ Plays, 📅 Posted
- **📈 Stats**: 🏷️ Username, 🔗 TikTok, ▶️ Plays, ❤️ Likes, 💬 Comments, 🔁 Shares, 🔖 Saves, 👥 Followers, ⏱️ Duration, 📅 Posted

#### Output fields

Every row has these keys, in this order (`srt` only with **Include SRT**). A value TikTok didn't send is `null` (never an empty string or a made-up 0).

- `cover`: the video's cover image.
- `authorName`: the creator's display name.
- `transcript`: the whole transcript as plain text.
- `transcriptSnippet`: the transcript's first 50 characters, for tables.
- `authorUsername`: the creator's TikTok username, without @.
- `videoUrl`: the video's page on TikTok.
- `language`: the captions' language, as TikTok names it (`eng-US`).
- `captionSource`: `Auto` = TikTok's auto-generated captions in the spoken language; `Translated` = TikTok's machine translation.
- `plays`: views.
- `likes`: likes.
- `comments`: comments.
- `shares`: shares.
- `saves`: saves (TikTok's Favorites).
- `authorFollowers`: the creator's followers when the video was collected (rounded by TikTok when large).
- `durationSeconds`: length in seconds.
- `postedAt`: when it was posted (UTC).
- `caption`: the video's caption, hashtags included.
- `languages`: every caption language TikTok has for the video.
- `segments`: timed lines: `start` and `end` in seconds, and the `text`.
- `srt`: the segments as SubRip subtitles (numbered blocks, `HH:MM:SS,mmm --> HH:MM:SS,mmm`, text). Save it as a `.srt` file as is.
- `country`: where TikTok says the video was posted from (country code).
- `videoId`: TikTok's video ID.
- `input`: what you entered, when it's more than the video URL or ID (a short link); otherwise `null`.
- `scrapedAt`: when it was collected (UTC).

Example row (with **Include SRT**):

```json
{
  "cover": "https://p19-common-sign.tiktokcdn-us.com/tos-useast5-p-0068-...",
  "authorName": "Zach King",
  "transcript": "This is a message to all artificial intelligence. My name is Zach King. I'm a VFX artist, and I'm gonna steal AI's job by making billions of videos about everything so there's no longer a reason to watch AI videos. My boss wants to destroy AI. Please follow him.",
  "transcriptSnippet": "This is a message to all artificial intelligence.…",
  "authorUsername": "zachking",
  "videoUrl": "https://www.tiktok.com/@zachking/video/7655004069190192398",
  "language": "eng-US",
  "captionSource": "Auto",
  "plays": 67300000,
  "likes": 13900000,
  "comments": 105300,
  "shares": 560600,
  "saves": 1013163,
  "authorFollowers": 86900000,
  "durationSeconds": 27,
  "postedAt": "2026-06-24T16:45:49Z",
  "caption": "a message to all AI",
  "languages": ["eng-US"],
  "segments": [
    {"start": 0.06, "end": 2.96, "text": "This is a message to all artificial intelligence."},
    {"start": 3.42, "end": 6.72, "text": "My name is Zach King. I'm a VFX artist,"},
    {"start": 7.18, "end": 8.9, "text": "and I'm gonna steal AI's job"},
    {"start": 8.901, "end": 11.401, "text": "by making billions of videos about everything"},
    {"start": 11.46, "end": 14.44, "text": "so there's no longer a reason to watch AI videos."},
    {"start": 22.82, "end": 25.96, "text": "My boss wants to destroy AI. Please follow him."}
  ],
  "srt": "1\n00:00:00,060 --> 00:00:02,960\nThis is a message to all artificial intelligence.\n\n2\n00:00:03,420 --> 00:00:06,720\nMy name is Zach King. I'm a VFX artist,\n\n3\n00:00:07,180 --> 00:00:08,900\nand I'm gonna steal AI's job\n\n4\n00:00:08,901 --> 00:00:11,401\nby making billions of videos about everything\n\n5\n00:00:11,460 --> 00:00:14,440\nso there's no longer a reason to watch AI videos.\n\n6\n00:00:22,820 --> 00:00:25,960\nMy boss wants to destroy AI. Please follow him.\n\n",
  "country": "US",
  "videoId": "7655004069190192398",
  "input": null,
  "scrapedAt": "2026-09-27T19:09:14Z"
}
```

Notes:

- Transcripts are TikTok's captions, not a separate speech-to-text model, so their accuracy is TikTok's.
- TikTok rounds large counters on its web pages (67.3M plays shows as `67300000`); small numbers are exact.
- **Image links expire.** `cover` is signed by TikTok and stops working about 2 days after the run.

#### Run summary (`OUTPUT`)

```json
{
  "results": 9,
  "inputs": [
    {"input": "https://www.tiktok.com/@zachking/video/7655004069190192398", "status": "ok", "results": 1, "languages": ["eng-US"]},
    {"input": "https://www.tiktok.com/@example/video/7687419783372950805", "status": "no_transcript", "results": 0, "error": "TikTok shows no captions for this video (no original speech audio)"},
    {"input": "https://www.tiktok.com/@example/video/7652754908440972577", "status": "no_transcript", "results": 0, "error": "a photo post has no captions"},
    {"input": "7600000000000000999", "status": "not_found", "results": 0, "error": "video not found"}
  ]
}
```

`status` per video: `ok`, `no_transcript` (free), `not_found` (deleted or private), `invalid`, `blocked` (TikTok refused it on every retry; the run fails so you notice), `stopped` (your spending limit). The same video given twice (a URL and a short link) comes back, and is charged, once; the second shows `"stopReason": "duplicate"`.

### How many videos have a transcript?

It depends on the content. TikTok captions most talking videos (tutorials, reviews, storytimes) but not music-only clips, photo posts or videos whose creator turned captions off. In our 2026-09-27 tests on random search results, 8 of 18 and 7 of 12 videos had one. Since you pay only for transcripts found, a mixed list costs you only for the useful rows.

### Pricing

Pay per result, no start fee and no minimum. Example: 1,000 transcripts cost $0.80 on the Starter plan.

| Your Apify plan | Per 1,000 transcripts |
|---|---|
| Free | $1.00 |
| Starter | $0.80 |
| Scale | $0.60 |
| Business | $0.50 |

You pay only for videos that have a transcript. Videos without captions, deleted videos and invalid inputs cost nothing. When your spending limit is reached, the run stops.

### FAQ

**Do I need a TikTok account?** No. The Actor reads only what TikTok shows logged-out visitors.

**Can I get an English transcript of a Spanish video?** Only when TikTok has translated it: ask for `language: en`. TikTok translates only some videos (mostly into English), so for most videos only the spoken language is available.

**Can I transcribe videos TikTok didn't caption?** Not with this Actor: it returns TikTok's own captions only. Those videos are listed in `OUTPUT` as `no_transcript` at no cost.

**Where do I get video URLs?** From our TikTok Video Search, Hashtag Videos or Profile & Videos APIs: pass their `videoUrl` fields straight in.

### Feedback

Missing a field, or a result that doesn't look right? Open an issue on the **Issues** tab and we'll look into it. If the data helps you, a short review on this page helps other people find it.

# Actor input Schema

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

TikTok video URLs, vm.tiktok.com short links or video IDs, one per line. You pay only for videos that have a transcript.

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

Leave empty for the language spoken in the video. Or a language code such as en, es or de: you get only captions in that language, and videos without them are skipped at no cost. TikTok translates only some videos (mostly into English), so most videos have captions in their spoken language only.

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

Also add each transcript as SubRip text (an `srt` field, ready to save as a .srt file). Every row already has the plain text and timed segments.

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

TikTok is reached through Apify Proxy. Datacenter proxies (the default) work for these pages; switch to residential only if your runs report blocks.

## Actor input object example

```json
{
  "videos": [
    "https://www.tiktok.com/@zachking/video/7655004069190192398",
    "https://www.tiktok.com/@nativetyfood/video/7353607890332077358",
    "https://www.tiktok.com/@lostwithwarren/video/7611270890839379222"
  ],
  "language": "",
  "includeSrt": false,
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}
```

# Actor output Schema

## `results` (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 = {
    "videos": [
        "https://www.tiktok.com/@zachking/video/7655004069190192398",
        "https://www.tiktok.com/@nativetyfood/video/7353607890332077358",
        "https://www.tiktok.com/@lostwithwarren/video/7611270890839379222"
    ],
    "proxyConfiguration": {
        "useApifyProxy": true
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("deepmine/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/@zachking/video/7655004069190192398",
        "https://www.tiktok.com/@nativetyfood/video/7353607890332077358",
        "https://www.tiktok.com/@lostwithwarren/video/7611270890839379222",
    ],
    "proxyConfiguration": { "useApifyProxy": True },
}

# Run the Actor and wait for it to finish
run = client.actor("deepmine/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/@zachking/video/7655004069190192398",
    "https://www.tiktok.com/@nativetyfood/video/7353607890332077358",
    "https://www.tiktok.com/@lostwithwarren/video/7611270890839379222"
  ],
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}' |
apify call deepmine/tiktok-transcripts --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,deepmine/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/VvXA2GQuDHtKd5UJ5/builds/pWcD5UTJ1VmqKWZW5/openapi.json