# Instagram & TikTok Video Transcript (`alabs/social-video-transcript`) Actor

Paste Instagram Reel or TikTok video links. Get the transcript in the spoken language, the caption, public counters and the direct media link. No login, no cookies, no proxy.

- **URL**: https://apify.com/alabs/social-video-transcript.md
- **Developed by:** [Riad Mbarek](https://apify.com/alabs) (community)
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $12.00 / 1,000 transcriptions

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

## Instagram & TikTok Video Transcript

Paste Instagram Reel or TikTok links. Get the timestamped transcript, the caption and the public counters of each video as structured data. No login, no cookies, no proxy to set up.

### Use cases

#### Instagram Reel transcript for content research

Read what top creators say without watching 50 Reels. Paste a list of links, search the text for the topics, hooks and claims you care about.

#### TikTok transcript to text

Turn a TikTok into plain text you can search, quote (with credit), summarize or feed to your own tools. Each transcript comes with the caption, the account and the counters.

#### Reels to text, for repurposing

Use a Reel or a TikTok as the draft of a blog post, a newsletter or a thread. The full text and the segment list are in the same item, so you can keep the order and the wording.

#### Subtitles and accessibility

Every transcript comes in segments with `start` and `end` times in seconds. Convert them to SRT or VTT with a few lines of code, or keep the text as a readable version for people who cannot listen. The actor returns the segments, not a subtitle file.

#### Competitor and brand monitoring

Archive what a brand or a competitor publishes, in text form, next to its views, likes and comments. Sort by counters to see which videos work, then read why.

### How to use

1. **Paste the links.** Public Instagram Reel/post or TikTok video links, one per line, up to 100 per run.
2. **Press Start.** Language is detected for each video. The default settings fit most cases.
3. **Get your data.** Export the dataset as JSON, CSV or Excel from the run page, or read it through the Apify API.

### Input

| Field | What it does | Default |
|---|---|---|
| `urls` | Public Instagram Reel/post or TikTok video links, one per line (max 100 per run) | — |
| `transcribeWhenNoSubtitles` | Turn off to get only caption, counters and media link | on |
| `whisperModel` | `base` (fast) or `small` (more accurate, about 3× slower) | `base` |
| `maxDurationSeconds` | Longer videos come back without transcript (30 to 3600) | 600 |

```json
{
  "urls": [
    "https://www.instagram.com/reel/DbOpZRiD2M7/",
    "https://www.tiktok.com/@maverickgpt/video/7661705764901227807"
  ]
}
```

### Output example

One dataset item per link. This is a real TikTok result (caption, text, segments and media link shortened here):

```json
{
  "url": "https://www.tiktok.com/@maverickgpt/video/7661705764901227807",
  "platform": "tiktok",
  "status": "ok",
  "error": null,
  "note": null,
  "account": "maverickgpt",
  "title": "Comment “Skills” and I’ll send you my full list 👇 Claude has over 50,...",
  "caption": "Comment “Skills” and I’ll send you my full list 👇 Claude has over 50,000 skills and most people have never used one. Here are 5 to get you ahead of 99% of people. 1. Stop Slop …",
  "durationSec": 52.69,
  "counts": { "views": 28000, "likes": 1385, "comments": 159, "followers": null },
  "mediaUrl": "https://v19-webapp-prime.tiktok.com/video/…",
  "mediaUrlKind": "muxed",
  "route": "ytdlp",
  "transcript": {
    "source": "whisper-base",
    "language": "en",
    "text": "Clod has over 50,000 skills and most people have never even used one. So here are five to get you ahead of 99% of people. Number one is the stop-slop skill. …",
    "segments": [
      { "start": 0.0, "end": 3.2, "text": "Clod has over 50,000 skills and most people have never even used one." },
      { "start": 3.2, "end": 5.32, "text": "So here are five to get you ahead of 99% of people." },
      { "start": 5.32, "end": 7.04, "text": "Number one is the stop-slop skill." }
    ]
  }
}
```

What the fields tell you:

- `status` is `ok` or `error`. On `error`, the reason is in `error`; the rest is empty.
- `note` explains an `ok` item without transcript (no speech detected, post without video).
- `transcript.source` is `whisper-base`, `whisper-small` or `none` (nothing to transcribe).
- `counts` holds what the platform shows. A counter it hides comes back as `null` (here, `followers`).
- `mediaUrl` is a temporary link to the video file. Download it soon after the run.

### Pricing

You pay **per transcription delivered**. Links that fail, videos with no speech and runs with transcription turned off are not charged as transcriptions.

### Limits

- **Public posts only.** Private accounts, stories and deleted posts return an error item with the reason. Some Instagram posts that look public can still fail (embed turned off by the owner, or Instagram changed its page).
- **Instagram and TikTok.** X (Twitter) posts are in beta. YouTube is not supported: YouTube blocks cloud servers, so the run would fail. Use a dedicated YouTube transcript tool.
- **Video length.** Videos longer than `maxDurationSeconds` (600 s by default, 3600 s at most) come back without transcript, with caption and counters.
- **Posts without video.** Image posts and carousels return an item with a `note` and nothing to transcribe.
- **No speech.** Music-only videos return an empty transcript (`source: none`).
- **Languages.** Any spoken language: the language is detected per video (Whisper covers about 99 languages). French and English are tested in depth; accuracy varies by language. On clips under 10 seconds the detection can be wrong; use `small`.
- **Accuracy.** The transcript comes from Whisper. Brand names and jargon can be misheard (the example above writes “Clod” for “Claude”). Use `small` for better results and check names before you publish.
- **Counters.** Views, likes and comments appear only when the platform shows them.

### FAQ

**Do I need to log in or give cookies?**
No. Paste public links and press Start. There is no proxy to configure.

**Which languages does it handle?**
Any spoken language: it is detected for each video (Whisper covers about 99 languages). French and English are tested in depth; accuracy varies by language, so test a few links before a large run.

**Can I get only the caption and the counters?**
Yes. Turn off `transcribeWhenNoSubtitles`. You get caption, account, counters and media link, and no transcription is charged.

**Can I republish a transcript?**
Use the tool on content you are allowed to process. Transcripts of other people's videos suit research, accessibility and analysis. Do not republish them as your own.

# Actor input Schema

## `urls` (type: `array`):

Public links to Instagram Reels/posts or TikTok videos, one per line. X posts are in beta. YouTube is not supported (it blocks cloud servers).

## `transcribeWhenNoSubtitles` (type: `boolean`):

The audio is transcribed with Whisper, language auto-detected. Turn off to get only caption, counters and media link (faster, not charged as a transcription).

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

base is fast; small is more accurate and about 3 times slower.

## `maxDurationSeconds` (type: `integer`):

Longer videos are returned without transcript (caption and counters only).

## Actor input object example

```json
{
  "urls": [
    "https://www.tiktok.com/@maverickgpt/video/7661705764901227807"
  ],
  "transcribeWhenNoSubtitles": true,
  "whisperModel": "base",
  "maxDurationSeconds": 600
}
```

# Actor output Schema

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

One item per link: transcript with timestamps, caption, public counters and media link.

# 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 = {
    "urls": [
        "https://www.tiktok.com/@maverickgpt/video/7661705764901227807"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("alabs/social-video-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 = { "urls": ["https://www.tiktok.com/@maverickgpt/video/7661705764901227807"] }

# Run the Actor and wait for it to finish
run = client.actor("alabs/social-video-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 '{
  "urls": [
    "https://www.tiktok.com/@maverickgpt/video/7661705764901227807"
  ]
}' |
apify call alabs/social-video-transcript --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,alabs/social-video-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/aeh9Vf3nf66AXKg7P/builds/wjWtcwPVp83VTxwfL/openapi.json