# Instagram Transcript Scraper (`transcriptfetch/instagram-transcript-scraper`) Actor

Transcripts of Instagram Reels and video posts, one by one or a whole profile's newest. AI transcription of the audio, with timestamps. Failed videos are free.

- **URL**: https://apify.com/transcriptfetch/instagram-transcript-scraper.md
- **Developed by:** [Transcript Fetch](https://apify.com/transcriptfetch) (community)
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event

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 Transcript Scraper

Get the transcript of any public Instagram Reel, or of a whole profile's newest posts, as plain text and as timestamped segments. Instagram videos rarely have captions, so this actor transcribes their audio with AI. Use it to summarize Reels, research what creators and brands in a niche are saying, repurpose content, build subtitles or feed an AI pipeline.

### What you get

- **Reel links in, transcripts out.** Paste Instagram Reel links and get each one's full text.
- **Whole profiles.** Add a profile (username or link) and the actor transcribes its newest posts, up to the limit you set, with each post's caption, publish date and play count.
- **AI transcription when there are no captions.** The spoken language is detected automatically. Prefer to skip videos without captions? Choose **Captions only** and you never pay for AI transcription.
- **Timestamps.** Each line comes with its start time and length, or turn them off and keep just the text.
- **Failed videos are free.** Private, deleted, photo-only or music-only posts come back as a row that says why, at no charge.

### Input

| Field | What it is |
| --- | --- |
| `videoUrls` | Instagram Reel links. |
| `profiles` | Instagram profiles, as `username` or `https://www.instagram.com/username/`. |
| `maxVideosPerSource` | How many of each profile's newest posts to transcribe (default 10). |
| `transcriptSource` | `auto` (captions, else AI transcription), `captions` (captions only), or `audio` (always AI). |
| `includeTimestamps` | Adds timestamped `segments` next to the full `text` (default on). |

```json
{
  "videoUrls": ["https://www.instagram.com/reel/DeroUGDhF2D/"],
  "profiles": ["natgeo"],
  "maxVideosPerSource": 10,
  "transcriptSource": "auto",
  "includeTimestamps": true
}
```

### Output

One row per video. A real row, shortened:

```json
{
  "inputUrl": "https://www.instagram.com/reel/DeroUGDhF2D/",
  "url": "https://www.instagram.com/reel/DeroUGDhF2D/",
  "platform": "instagram",
  "videoId": "DeroUGDhF2D",
  "title": "new NBA season prep with @jordanclarksons and @cbrickley603 🏀 …",
  "author": null,
  "publishedAt": null,
  "plays": null,
  "durationSeconds": 87,
  "language": "en",
  "transcriptSource": "ai_transcription",
  "text": "Three more chances to do this. What up, what up, it's Steve Brick. Jordan Clarkson. About to show you some drills. Let's get it. …",
  "segments": [
    { "start": 0, "duration": 29.3, "text": "Three more chances to do this. What up, what up, it's Steve Brick. …" },
    { "start": 29.3, "duration": 29.5, "text": "Yeah, pull up hit range. Three ball for goal. Game time. …" }
  ],
  "status": "ok"
}
```

A video that could not be transcribed has `"status": "failed"` with an `errorCode` (for example `not_public`, `no_video` or `no_speech`) and an `errorMessage`, and costs nothing. Export the dataset as JSON, CSV or Excel, or read it through the Apify API.

### Pricing

Pay per event, only for transcripts you receive:

- **AI transcription**: one per started 5 minutes of audio. Almost every Reel is under 5 minutes, so that is one per Reel.
- **Transcript**: one per video whose transcript came from its captions, in the rare case it has them.

Failures, profile listings and links that are not Instagram videos are never charged. Set a maximum charge for a run in its options and the actor stops before going over it.

### Other platforms

- [TikTok Transcript Scraper](https://apify.com/transcriptfetch/tiktok-transcript-scraper): videos and whole profiles.
- [YouTube Transcript Scraper](https://apify.com/transcriptfetch/youtube-transcript-scraper): videos, Shorts, channels and playlists.

### Using it from code or an AI assistant

This actor runs on [TranscriptFetch](https://transcriptfetch.com), a transcript API for YouTube, TikTok and Instagram. If you would rather call it directly, TranscriptFetch has a REST API, an MCP server for Claude and ChatGPT, and a no-code dashboard: see [transcriptfetch.com/docs](https://transcriptfetch.com/docs).

### FAQ

**Which languages are supported?** AI transcription detects the spoken language by itself.

**How long does it take?** AI transcription of a Reel usually finishes within a minute; the actor works on several videos at once.

**Does it read private videos?** No. It reads only what is publicly viewable without logging in, and never needs your Instagram account.

**Is scraping Instagram transcripts legal?** The actor reads only public videos. How you use the transcripts is up to you: respect copyright and the creators' rights, and check with a lawyer if you are unsure about your use.

**Something went wrong?** Open an issue on this actor's Issues tab and include the run's link.

# Actor input Schema

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

Instagram Reel and video links (instagram.com/reel/…).

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

Instagram profiles as links (instagram.com/user/) or usernames. Each profile's newest posts are transcribed, up to the limit below.

## `maxVideosPerSource` (type: `integer`):

How many of each profile's newest videos to transcribe.

## `transcriptSource` (type: `string`):

Instagram videos rarely have captions, so the default transcribes their audio with AI. 'Captions only' skips videos without captions and never charges for AI transcription.

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

Adds `segments` (start, duration and text of each line) next to the full `text`.

## Actor input object example

```json
{
  "videoUrls": [
    "https://www.instagram.com/reel/DeroUGDhF2D/"
  ],
  "maxVideosPerSource": 10,
  "transcriptSource": "auto",
  "includeTimestamps": true
}
```

# Actor output Schema

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

One row per Instagram video: url, title, author, publishedAt, durationSeconds, language, transcriptSource (captions or ai_transcription), text, segments (start, duration, text) and status; failed rows carry errorCode and errorMessage.

# 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.instagram.com/reel/DeroUGDhF2D/"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("transcriptfetch/instagram-transcript-scraper").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.instagram.com/reel/DeroUGDhF2D/"] }

# Run the Actor and wait for it to finish
run = client.actor("transcriptfetch/instagram-transcript-scraper").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.instagram.com/reel/DeroUGDhF2D/"
  ]
}' |
apify call transcriptfetch/instagram-transcript-scraper --silent --output-dataset

```

## MCP server setup

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

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/8H24zl6iw5s4EK9Lm/builds/gHWNzVaGbpaCTm6Ur/openapi.json