# Instagram Video Transcript: Reels to Text, Hooks & Scripts (`pikoulas/instagram-transcripts`) Actor

Turn Instagram Reels and videos into text: the full script, the opening hook and timestamped lines, by reel URL or a creator's whole profile, with caption, likes, comments and date. For creators, marketers and AI pipelines. Whisper inside the run, ~100 languages. $3 per 1,000 reels.

- **URL**: https://apify.com/pikoulas/instagram-transcripts.md
- **Developed by:** [Spyridon Pikoulas](https://apify.com/pikoulas) (community)
- **Categories:** Social media, Videos, AI
- **Features:** Limited permissions
- **Stats:** 1 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $3.00 / 1,000 audio minute transcribed (whisper base)s

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 Video Transcript

Turn Instagram Reels and videos into text: the whole script, the **hook** (the line spoken in the
first 3 seconds) and timestamped lines, for what a reel says rather than what its caption says.
Built for creators studying what works in their niche, marketers tracking what creators say
about a product, and AI pipelines that need reels as text. No account or browser, from two kinds
of source:

- **Reels:** by URL (instagram.com/reel/..., /p/... or /tv/... for a video post) or shortcode.
- **Profiles:** a creator's reels and videos, newest first, as far back as the profile goes, by
  username, @handle or URL.

The speech-to-text runs inside the actor: OpenAI's Whisper model, open source, on Apify's
servers. Nothing is sent to an outside AI service. It detects the language spoken in each reel,
among about 100.

Every result also carries the reel's caption, hashtags and mentions, date, length, likes and
comments, audio track, cover image and video link, and its author's username, name and verified
badge, with the creators of collab posts.

It costs **$3 per 1,000 reels** under a minute, on every Apify plan, the free one too, then
$0.003 for each further started minute, with Whisper base; Whisper small is $0.008 a minute.
Reels without speech are free.

### What people use it for

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

### How to transcribe Instagram Reels

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

**Speech-to-text model** picks between Whisper base, fast and good on clear speech, and Whisper
small, more accurate on accents, noise, names and languages other than English, and about three
times slower. **Language** fixes the language spoken when you know it; otherwise each reel's is
detected. **Translate to English** gives the text in English whatever the language spoken, at the same price; off, a transcript is always in the language spoken, never translated. Turn on **Include timestamps** for `segments`, each line with its start
and end, **Subtitle files** for each transcript as .srt and .vtt subtitles, free, and **Skip
reels without speech** to get transcripts only.

```json
{
  "reels": ["https://www.instagram.com/reel/DfIfj7vS3qt/"],
  "profiles": ["hubermanlab", "https://www.instagram.com/nasa/"],
  "maxReelsPerProfile": 50,
  "publishedAfter": "2026-09-01",
  "model": "base",
  "includeTimestamps": true,
  "skipReelsWithoutSpeech": true
}
```

An Instagram URL works in either list: a reel URL pasted under profiles is read as a reel.

### Output

```json
{
  "id": "3976680007546796844",
  "code": "DcwAWXDOXss",
  "url": "https://www.instagram.com/reel/DcwAWXDOXss/",
  "isReel": true,
  "caption": "Comment “Andrew” and we’ll personally DM you the full conversation. …",
  "hashtags": ["rajshamani", "figuringout"],
  "mentions": ["hubermanlab"],
  "createdAt": "2026-09-01T15:40:05Z",
  "durationSeconds": 132.9,
  "likes": 867525,
  "comments": 11505,
  "authorUsername": "figuringout.co",
  "authorName": "Figuring Out with Raj Shamani",
  "authorVerified": false,
  "authorId": "51609571959",
  "coauthors": ["hubermanlab", "rajshamani"],
  "audioTitle": "Andrew Huberman",
  "audioArtist": "figuringout.co",
  "hasAudio": true,
  "thumbnailUrl": "https://scontent-iad3-1.cdninstagram.com/v/t51.82787-15/791245678_….jpg",
  "videoUrl": "https://scontent-iad3-1.cdninstagram.com/o1/v/t2/f2/m86/AQMDiHbV….mp4",
  "input": "hubermanlab",
  "language": "en",
  "languageProbability": 1,
  "hook": "The person that can turn their mind off in the final hour of their day",
  "text": "The person that can turn their mind off in the final hour of their day and get the better, deeper sleep, and put all my money on that person. …",
  "billedMinutes": 3,
  "segments": [{"start": 0, "end": 3.68, "text": "The person that can turn their mind off in the final hour of their day"}]
}
```

A reel without speech (no sound, or music only) 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~instagram-transcripts/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"reels": ["https://www.instagram.com/reel/DfIfj7vS3qt/"], "profiles": ["hubermanlab"], "maxReelsPerProfile": 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/instagram-transcripts",
      "headers": {"Authorization": "Bearer YOUR_APIFY_TOKEN"}
    }
  }
}
```

Then ask in plain words, for example: "Transcribe @hubermanlab's last 5 reels and compare their opening hooks." 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 transcribe Instagram Reels?

With Whisper base you pay **$0.003 per started minute of audio**, on every plan: most reels
are under a minute, so $3 per 1,000 reels, and a 2½-minute reel is $0.009. Whisper small, which takes about three times the computing,
is $0.008 per started minute. `billedMinutes` shows each reel's. Reels without speech are free, and so is
everything else the run fetches. The only other charge is traffic through Apify's residential
proxy, at $0.0012 per 100 KB, in runs that use it: only when Instagram refuses Apify's own IPs,
or when you set the proxy yourself. There are no monthly fees.

### Good to know

- Whisper writes what it hears: names, slang and words drowned in music can come out wrong, and
  Whisper small gets more of them right. Captions burned into the video aren't read, only speech.
- A run transcribes about seven minutes of audio a minute with Whisper base at the default 4 GB
  of memory, and under three with Whisper small. More memory is faster, at the same price per
  minute.
- Instagram doesn't show view counts to visitors who aren't logged in, so there are none; likes
  are empty when the creator hides them.
- A reel found under several profiles, or both by URL and in a profile, is given once per run.
- Private accounts, and deleted, private or age-restricted reels can't be read; the log names
  them. Photos and carousels are left out.
- `videoUrl` and `thumbnailUrl` are Instagram's signed links, which expire after some days.

### FAQ

#### Is it legal to scrape Instagram?

It collects only what Instagram shows publicly, without logging in. [Instagram's robots.txt](https://www.instagram.com/robots.txt) prohibits automated collection without its written permission, 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.

#### How do I get subtitles for a reel?

Turn on **Subtitle files**: each transcript comes with an .srt and a .vtt file, linked from its
row as `srtUrl` and `vttUrl`, at no extra cost.

#### 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), [TikTok](https://apify.com/pikoulas/tiktok-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

## `reels` (type: `array`):

Reel or video post URLs (instagram.com/reel/..., /p/..., /tv/...) or their shortcodes.

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

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

## `maxReelsPerProfile` (type: `integer`):

Reels and videos from each profile, newest first. Photos and carousels are left out.

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

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

## `model` (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, takes about three times as long and costs $0.008 per started minute against base's $0.003 ($0.016 and $0.006 on Apify's free plan).

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

The language spoken, as a code (en, es, pt, de, hi...), when all the reels share one. Empty: detected for each reel.

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

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

## `subtitles` (type: `boolean`):

Also saves each transcript as .srt and .vtt subtitles in the run's key-value store, linked from its row as srtUrl and vttUrl. Free.

## `translateToEnglish` (type: `boolean`):

The text in English, whatever the language spoken, translated by Whisper as it transcribes. Off: the language spoken, never translated. Same price.

## `skipReelsWithoutSpeech` (type: `boolean`):

Leaves out reels with no sound or nothing spoken (music only), so the count per profile counts transcripts. Otherwise they come with their details and the reason, free.

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

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

## Actor input object example

```json
{
  "reels": [
    "https://www.instagram.com/reel/DfIfj7vS3qt/"
  ],
  "maxReelsPerProfile": 20,
  "model": "base",
  "language": "",
  "includeTimestamps": false,
  "subtitles": false,
  "translateToEnglish": false,
  "skipReelsWithoutSpeech": 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 = {
    "reels": [
        "https://www.instagram.com/reel/DfIfj7vS3qt/"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("pikoulas/instagram-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 = { "reels": ["https://www.instagram.com/reel/DfIfj7vS3qt/"] }

# Run the Actor and wait for it to finish
run = client.actor("pikoulas/instagram-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 '{
  "reels": [
    "https://www.instagram.com/reel/DfIfj7vS3qt/"
  ]
}' |
apify call pikoulas/instagram-transcripts --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,pikoulas/instagram-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/dnzInhG3uaNFT4lIn/builds/TAVzQqZdIPGOTdZ7d/openapi.json
