# Instagram Reels & TikTok Transcript: Hooks + Subtitles (`benexe/reels-tiktok-transcript`) Actor

Transcribe Instagram Reels and TikTok videos with Whisper: full transcript, the first-3-seconds hook, language, timestamps and SRT/VTT subtitles. From profiles, links or your scraper datasets. Pay per video.

- **URL**: https://apify.com/benexe/reels-tiktok-transcript.md
- **Developed by:** [Marcel Tomas](https://apify.com/benexe) (community)
- **Categories:** Social media, AI, Videos
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $2.50 / 1,000 video transcribeds

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

## Instagram Reels & TikTok Transcript: Hooks + Subtitles

**Turn any Instagram Reel or TikTok into text in seconds — full transcript, the first-3-seconds hook, language and subtitles, from $0.004 per video.**

Study what makes short videos work, repurpose your own content, or feed transcripts to your AI tools. Paste profiles or links, get clean transcripts. No subscription, no browser extension, no copy-paste.

- ✅ Instagram Reels + TikTok in one run
- ✅ Whisper large-v3 turbo, 99+ languages
- ✅ The **hook** (first seconds) as its own field
- ✅ Views, likes, caption and date next to every transcript
- ✅ SRT/VTT subtitles
- ✅ Music-only videos are free

### Why this Actor

| | This Actor | Typical options |
|---|---|---|
| Price per video | **$0.004** (up to 3 min), $0.0015 with your own Groq key | $0.015–0.075 per reel, or $0.048 per minute as a scraper add-on |
| Hook extraction | Yes, configurable (default first 3 s) | Rarely |
| Instagram + TikTok | Both, plus your own scraper datasets and direct video files | Usually one platform |
| Videos without speech | **Free** (music-only, silent) | Charged |
| Subscriptions | None, pay per video | $49–499/month creator tools |

### How it works

1. **Collect videos.** Profiles and links are collected with the official [Instagram Reel Scraper](https://apify.com/apify/instagram-reel-scraper) and [TikTok Scraper](https://apify.com/clockworks/tiktok-scraper), run inside your own Apify account (you pay those Actors' usual small per-video price). Already scraped? Pick your datasets instead — no scraping cost.
2. **Transcribe.** The audio is extracted and transcribed with Whisper large-v3 turbo.
3. **Deliver.** One record per video with transcript, hook, language, timestamps, stats and optional subtitles.

### Example

Input:

```json
{
  "instagram": ["natgeo", "https://www.instagram.com/reel/DfKYi32MhCn/"],
  "tiktok": ["@nasa"],
  "maxVideosPerProfile": 10,
  "includeSubtitles": true
}
```

Output (real run, shortened):

```json
{
  "platform": "instagram",
  "url": "https://www.instagram.com/p/DfNzJy_gKtl/",
  "owner": "natgeo",
  "views": 2044789,
  "likes": 73483,
  "comments": 215,
  "postedAt": "2026-11-01T22:26:13.000Z",
  "durationSec": 90.9,
  "status": "ok",
  "language": "English",
  "hook": "Usually when we work with specimens, we just work with the actual bones themselves.",
  "transcript": "Usually when we work with specimens, we just work with the actual bones themselves. …",
  "wordCount": 207,
  "wordsPerMinute": 138,
  "segments": [{ "start": 0, "end": 3.76, "text": "Usually when we work with specimens, …" }],
  "srt": "1\n00:00:00,000 --> 00:00:03,760\n…"
}
```

A 91-second reel transcribed in under 4 seconds.

### Use cases

- **Creators and social media managers:** collect the hooks and scripts of the best-performing videos in your niche.
- **Agencies and brands:** analyse competitors' content at scale; build swipe files.
- **Repurposing:** turn your reels into blog posts, threads, newsletters and captions.
- **AI workflows:** n8n, Make, Zapier, the Apify API or MCP (Claude, ChatGPT, Cursor) — send profiles, get transcripts.
- **Research:** study messaging, trends and language across thousands of short videos.

### Input

| Field | What it does |
|---|---|
| Instagram reels or profiles | Reel URLs, profile URLs or usernames. Profiles: latest *N* reels. |
| TikTok videos or profiles | Video URLs (incl. short links), profile URLs or @usernames. |
| Datasets from a previous scraper run | Datasets from Instagram Reel Scraper, Instagram Scraper or TikTok Scraper (video download on). |
| Direct video or audio URLs | MP4, MOV, WebM, M4A, MP3, WAV, OGG, FLAC. |
| Videos per profile / Only newer than / Max videos | Limits. |
| Language | Empty = automatic detection. |
| Hook length | Seconds counted as the hook (default 3). |
| Your Groq API key | Optional: lower price, no free-plan cap. |

### Pricing (pay per event)

| Event | Free plan | Paid plans |
|---|---|---|
| `video-transcribed` — one video transcribed (up to 3 minutes) | $0.004 | down to $0.0025 |
| `extra-minute` — each started minute beyond 3 minutes | $0.002 | $0.002 |
| `video-transcribed-byok` — one video with your own Groq key (any length) | $0.0015 | down to $0.001 |

**Never charged:** videos without speech, videos that cannot be downloaded, failed transcriptions. Collecting from profiles and links also runs the official scrapers in your account at their own price (about $0.003–0.005 per video). Without your own key, free-plan accounts can transcribe up to 25 videos per run.

### FAQ

**Which languages?** Whisper large-v3 turbo supports 99+ languages and detects the language automatically.

**Is my data stored?** Videos are downloaded into your run, processed and deleted. Results stay in your Apify storage. The audio track is sent to Groq's Whisper API for transcription (with your own key, under your Groq account).

**Why "transcribe right after scraping" for datasets?** Instagram and TikTok video links expire within hours. Videos with expired links come back as errors and are not charged.

**Private accounts?** Only public videos can be transcribed. The Actor never logs in.

**Long videos?** Supported up to 120 minutes per video (`maxMinutesPerVideo`, default 15).

### Good to know

- Transcribe only content you have the right to use. Respect the creators' rights when you republish.
- Transcript quality depends on audio: background music and cross-talk lower accuracy.

### Related

- [PDF, YouTube, Audio & Video to Markdown](https://apify.com/benexe/pdf-to-markdown-ocr) — documents, podcasts, YouTube and long videos to LLM-ready Markdown.
- [AI Image Upscaler](https://apify.com/benexe/ai-image-upscaler) — upscale thumbnails and covers 2x–4x or to 4K.
- [Website Contact Extractor](https://apify.com/benexe/website-contact-extractor) — emails, phones, socials and company data from any website or Google Maps results.

### Support

Open an issue on the Actor's *Issues* tab with the run ID. Feature requests welcome.

# Actor input Schema

## `instagram` (type: `array`):

Reel URLs, profile URLs or usernames (e.g. natgeo). For profiles, the latest reels are transcribed. Collected with Apify's official Instagram Reel Scraper in your account (billed by that Actor, about $0.0026 per reel).

## `tiktok` (type: `array`):

Video URLs (incl. vm.tiktok.com short links), profile URLs or @usernames. Collected with the TikTok Scraper by Clockworks in your account (billed by that Actor, about $0.005 per video incl. download).

## `datasetIds` (type: `array`):

Already scraped? Pick datasets produced by Instagram Reel Scraper, Instagram Scraper or TikTok Scraper (with video download on). No scraping cost. Run this right after scraping: platform video links expire within hours.

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

Direct links to MP4, MOV, WebM, M4A, MP3, WAV, OGG or FLAC files.

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

Latest videos to transcribe for each profile.

## `newerThan` (type: `string`):

Optional date (YYYY-MM-DD). Older videos from profiles are skipped.

## `maxVideos` (type: `integer`):

Hard cap for the whole run.

## `maxMinutesPerVideo` (type: `integer`):

Longer videos are transcribed up to this length.

## `transcriptionLanguage` (type: `string`):

Leave empty to detect the language automatically (99+ languages). Set it only if detection struggles.

## `hookSeconds` (type: `integer`):

The hook is what is said in the first N seconds.

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

Sentence-level segments with start/end seconds.

## `includeSubtitles` (type: `boolean`):

Ready-to-upload subtitle files in each record.

## `groqApiKey` (type: `string`):

Use your own free Groq key (console.groq.com) for the lower price per video and no free-plan cap. Groq bills you for the transcription itself.

## `healthCheck` (type: `boolean`):

Internal. Never charged.

## `healthProfile` (type: `string`):

Internal. Used only together with health check mode.

## Actor input object example

```json
{
  "instagram": [
    "natgeo"
  ],
  "maxVideosPerProfile": 10,
  "maxVideos": 200,
  "maxMinutesPerVideo": 15,
  "hookSeconds": 3,
  "includeSegments": true,
  "includeSubtitles": false,
  "healthCheck": false
}
```

# Actor output Schema

## `videos` (type: `string`):

Overview of every video: stats, hook, transcript, status.

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

Caption, hook and full transcript per video.

## `runSummary` (type: `string`):

Videos collected, transcribed, without speech, failed; stop reason.

# 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 = {
    "instagram": [
        "natgeo"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("benexe/reels-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 = { "instagram": ["natgeo"] }

# Run the Actor and wait for it to finish
run = client.actor("benexe/reels-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 '{
  "instagram": [
    "natgeo"
  ]
}' |
apify call benexe/reels-tiktok-transcript --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,benexe/reels-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/wpPeT6ibU7iCclLnt/builds/l0NWc8HAQnPSTobe6/openapi.json