# Instagram Transcript Scraper – Reels & Video to Text, AI (`tubetext/instagram-reels-transcript`) Actor

Instagram transcript API: turn Instagram Reels, videos and audio into text. Paste reel links or @usernames and get the spoken transcript, opening hook, timestamps or SRT plus plays, likes and caption. Whisper AI transcription, no login. $0.006 per reel, music-only and failed reels are free.

- **URL**: https://apify.com/tubetext/instagram-reels-transcript.md
- **Developed by:** [TubeText Labs](https://apify.com/tubetext) (community)
- **Categories:** Social media, Videos, AI
- **Stats:** 4 total users, 3 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $4.50 / 1,000 reel 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

## Instagram Transcript Scraper – Reels & Video to Text, AI

> By **TubeText Labs** – see all our tools at the end of this page.

Turn Instagram Reels into clean text for ChatGPT, Claude, RAG pipelines, content repurposing, hook research and competitor monitoring. Paste reel links **or @usernames** – for a profile, its latest public reels are transcribed. Works as an Instagram audio-to-text / speech-to-text tool: every reel's speech is transcribed with Whisper AI.

### Why this one

- 👤 **Profiles in, transcripts out** – give `@username` (or a profile link) and set how many reels you want. Newest first, with an optional date filter and "skip pinned".
- 🔁 **Only new reels** – turn on *Only new reels* and schedule the Actor: each run transcribes just what a creator posted since last time.
- 💸 **Pay only for results** – music-only reels, private or deleted reels and failed downloads are **free**.
- 🔇 **No junk transcripts** – Whisper "Thank you" loops, song-only audio and sound-effect clips are detected and not charged. Songs are detected after transcription and returned as free `lyrics` rows, so you only pay for real speech.
- 🎣 **Hook included** – a `hook` field with the opening line (first ~3 seconds), ready for hook and script research.
- 🔤 **On-screen text (optional)** – turn on `includeOnScreenText` and an AI vision model reads the captions, titles and stickers shown in the reel, one line each, in order. Works on music-only reels too (e.g. recipe reels that only show ingredient names). Adds about 5–10 s per reel; brand logos sometimes appear as a line.
- 📊 **Reel stats** – creator, caption, hashtags, posting time, plays (profile inputs), likes, comments, duration, follower count.
- 🧠 **AI-ready output** – plain text, timestamped sentences, SRT subtitles, raw segments and optional RAG chunks.
- 🔓 **No login, no cookies** – only public pages are used.

### Input example

```json
{
  "urls": [
    "@natgeo",
    "https://www.instagram.com/reel/DeK0nPogqrS/"
  ],
  "maxReelsPerProfile": 20,
  "onlyReelsNewerThan": "30 days",
  "skipAlreadyScraped": false
}
```

If you leave out `maxReelsPerProfile` (for example when calling the API), **20 reels per profile** are transcribed.

Accepted inputs: reel links (`instagram.com/reel/…`, `/p/…`), share links (`instagram.com/share/…`), profile links (`instagram.com/natgeo`, `…/natgeo/reels/`) and `@usernames`. Mix them freely. Already scraping Instagram with another Actor? Pass its dataset as `datasetId` (with `datasetSortBy` and `maxVideosFromDataset`) and the reels in it are transcribed.

### Output example

Real output (shortened) for `@natgeo` with *Max reels per profile* = 3:

```json
{
  "input": "@natgeo",
  "shortcode": "DeNJLoOksoN",
  "url": "https://www.instagram.com/reel/DeNJLoOksoN/",
  "ownerUsername": "natgeo",
  "ownerFullName": "National Geographic",
  "caption": "The shoebill’s prehistoric appearance makes it unique among living birds…",
  "hashtags": [],
  "postedAt": "2026-10-07T19:47:57Z",
  "durationSeconds": 105.2,
  "playCount": 415254,
  "likeCount": 42246,
  "commentCount": 171,
  "profileUsername": "natgeo",
  "pinned": false,
  "followerCount": 268419899,
  "status": "ok",
  "language": "en",
  "hook": "Did you know shoebills attack their own siblings?",
  "transcript": "Did you know shoebills attack their own siblings? Five surprising facts about the shoebill. They practice sibilicide. Shoebills typically lay two to three eggs per clutch…",
  "timestampedText": "[00:00] Did you know shoebills attack their own siblings? …",
  "wordCount": 254,
  "billedExtraMinutes": 0
}
```

`status` is `ok`, `no_speech` (music or sound effects only – free), `skipped` (no audio track, private, deleted or longer than your limit – free), `no_reels` or `error` (free). Also `profile_not_found_or_unavailable` (the username doesn't exist or isn't public – returned in seconds, free) and `no_new_reels` (with "only new reels" on and nothing new since the last run – free), and `lyrics` (the audio is a song, not speech – the song text is returned in a `lyrics` field, free).

`ownerUsername` is the reel's author; on collab reels it can be the co-author, so use `profileUsername` to group by the profile you asked for.

### Pricing

Pay per event:

- **$6.00 per 1,000 reels** (cheaper on higher Apify plans: down to $4.50). Each reel includes its first 3 minutes of audio – almost every reel is shorter.
- **$0.003 per extra started minute** for reels longer than 3 minutes.
- **+$0.002 per reel with on-screen text** when you turn it on, charged only when text is found.
- Music-only, private, deleted and failed reels are free.

Example: 1,000 typical reels (under 3 minutes) ≈ **$6.00**, minus the music-only ones.

### Use it from your tools

- **API / Python**: `client.actor("tubetext/instagram-reels-transcript").call(run_input={"urls": ["@natgeo"], "maxReelsPerProfile": 20})`, then read the default dataset.
- **n8n / Make / Zapier**: use the Apify integration, run this Actor and map the `transcript` and `hook` fields.
- **Monitoring**: schedule a run with your creator list and *Only new reels* on, then push new rows to Google Sheets, Notion or Slack.

### Ready-made examples

- [Instagram Reels to Text](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-reels-to-text)
- [All Reels of an Instagram Profile to Text](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-profile-reels-transcripts)
- [Instagram Video to Text and SRT](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-video-to-text-srt)
- [Instagram Reels Hooks Swipe File](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-reels-hooks-swipe-file)
- [Track New Reels Daily](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-reels-daily-tracker)
- [Instagram Reels On-Screen Text](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-reels-on-screen-text)
- [Instagram Reels for ChatGPT](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-reels-for-chatgpt)
- [Instagram Reels to SRT](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-reels-to-srt)
- [Competitor Reels Research](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-competitor-reels-research)
- [Reels Since a Date to Text](https://apify.com/tubetext/instagram-reels-transcript/examples/instagram-reels-only-new-since-date)

### TubeText Labs tools

**TubeText Labs** builds 9 pay-per-result Apify Actors for video, social and e-commerce data – no login, JSON/CSV/Excel output, and ready for ChatGPT and Claude (Apify MCP), n8n, Make and Zapier. All tools: [apify.com/tubetext](https://apify.com/tubetext)

**Transcripts**

- [YouTube Transcript Scraper](https://apify.com/tubetext/youtube-transcript-fast) – videos, Shorts, playlists and whole channels to text; Whisper AI when there are no captions
- [TikTok Transcript Scraper](https://apify.com/tubetext/tiktok-transcript) – TikTok captions plus Whisper AI, SRT and timestamps
- [Instagram Reels Transcript](https://apify.com/tubetext/instagram-reels-transcript) *(this tool)* – reel links or @usernames to text with Whisper AI

**Video & ad analysis**

- [Video Breakdown AI](https://apify.com/tubetext/video-breakdown-ai) – hook analysis, shot list, cut pacing, products shown and script of any TikTok, Reel or YouTube video
- [Video Ad Analyzer](https://apify.com/tubetext/video-ad-analyzer) – competitors' YouTube video ads by brand or domain (Google Ads Transparency), torn down by AI

**Channel analytics**

- [YouTube Channel Analytics](https://apify.com/tubetext/youtube-channel-analytics) – subscribers, recent video performance, Social Blade grade, ranks and estimated earnings

**E-commerce & travel**

- [TikTok Shop Product Scraper](https://apify.com/tubetext/tiktok-shop-product-scraper) – US TikTok Shop prices, items sold, stock per SKU and shop stats
- [AliExpress Search Scraper](https://apify.com/tubetext/aliexpress-search-scraper) – AliExpress search results by keyword: price, items sold, rating, shipping, badges
- [Google Hotels Scraper](https://apify.com/tubetext/google-hotels-scraper) – hotel prices for any destination and dates, per booking site and as a 90-day price calendar

### FAQ

**How many reels can I get from a profile?** Set *Max reels per profile* to any number up to 1,000 (default 20). Large profiles take longer; our production tests went up to 40 reels per profile. Reels are read from the profile's public Reels tab, newest first; pinned reels come first unless you skip them.

**Why did a reel return `no_speech`?** It contains only music or sound effects. These are never charged.

**Why did a reel come back as `lyrics`?** Its audio is a song rather than someone talking. You still get the song text in the `lyrics` field, but the row isn't charged. When it's unclear, the reel is treated as speech.

**Private accounts?** Not supported – only public profiles and reels. Private accounts return an error row for free.

**Which languages?** Whisper detects the spoken language automatically (90+ languages, including Spanish, Japanese and Chinese); the transcript is in the original language.

**How fast is it?** About 15 reels per minute with default settings – 100 reels usually take under 10 minutes, including reading the profiles. Speed varies with Instagram's rate limits.

**Is this legal?** The Actor only reads publicly available pages, without logging in, and does not collect emails, phone numbers or comments. You are responsible for how you use the data (copyright, privacy and Instagram's terms).

**Can I cap what a run costs?** Yes – set *Maximum cost per run* in the run options. The run stops cleanly when the next item would go over it: you are never charged more, and you get a clear "stopped at your limit" status message.

**What happens if a big run hits the time limit?** It stops cleanly shortly before the limit: everything finished so far is delivered, the run ends as succeeded, and the status message says how many items weren't started. Raise the run timeout, or run again with *Only new* turned on to continue where it stopped.

**Am I charged if a reel fails?** No. Private, deleted and failed reels, and music-only reels, come back with a status and are not charged – you only pay for reels that were actually transcribed.

# Actor input Schema

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

Mix freely, one per line: reel links (instagram.com/reel/…, /p/…), share links (instagram.com/share/…), profile links (instagram.com/natgeo or …/natgeo/reels/) or @usernames. For a profile, its latest public reels are transcribed.

## `datasetId` (type: `string`):

A dataset from another Actor run, e.g. an Instagram post, hashtag or profile scraper (pick it, or paste its ID via API). The reel/post links in it are transcribed. Read-only access to this one dataset is requested.

## `datasetSortBy` (type: `string`):

Which reels to take first when the dataset has more than 'Max videos from dataset'.

## `maxVideosFromDataset` (type: `integer`):

How many reel links to take from the dataset (each is billed like a single reel).

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

Newest reels first (the profile's Reels tab order). Ignored for direct reel links.

## `onlyReelsNewerThan` (type: `string`):

Optional. A date (2026-09-01) or a relative period (7 days, 2 weeks, 3 months). Applies to profiles.

## `skipAlreadyScraped` (type: `boolean`):

For scheduled monitoring: remembers which reels of each profile were already processed (in a named key-value store 'tubetext-instagram-seen' in your account) and skips them next time.

## `skipPinned` (type: `boolean`):

Pinned reels sit at the top of a profile even when they are old.

## `maxMinutesPerReel` (type: `integer`):

Longer videos are skipped (free) to keep costs predictable.

## `includeTimestampedText` (type: `boolean`):

Adds a 'timestampedText' field with one \[mm:ss] line per sentence.

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

Adds an 'srt' field in SubRip (.srt) format.

## `includeOnScreenText` (type: `boolean`):

Also read the text shown in the video (captions, titles, text stickers) with an AI vision model. Works on music-only reels too. Slower; billed as an extra 'on-screen-text' event only for reels where text was found.

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

Adds a 'segments' array with start, duration and text.

## `chunkWords` (type: `integer`):

Set e.g. 300 to add a 'chunks' array: transcript split into ~N-word blocks with start/end timestamps. 0 = off.

## `maxConcurrency` (type: `integer`):

How many reels to process in parallel.

## Actor input object example

```json
{
  "urls": [
    "@natgeo"
  ],
  "datasetSortBy": "views",
  "maxVideosFromDataset": 50,
  "maxReelsPerProfile": 3,
  "skipAlreadyScraped": false,
  "skipPinned": false,
  "maxMinutesPerReel": 15,
  "includeTimestampedText": true,
  "includeSrt": false,
  "includeOnScreenText": false,
  "includeSegments": false,
  "chunkWords": 0,
  "maxConcurrency": 8
}
```

# Actor output Schema

## `transcripts` (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 = {
    "urls": [
        "@natgeo"
    ],
    "maxReelsPerProfile": 3
};

// Run the Actor and wait for it to finish
const run = await client.actor("tubetext/instagram-reels-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": ["@natgeo"],
    "maxReelsPerProfile": 3,
}

# Run the Actor and wait for it to finish
run = client.actor("tubetext/instagram-reels-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": [
    "@natgeo"
  ],
  "maxReelsPerProfile": 3
}' |
apify call tubetext/instagram-reels-transcript --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,tubetext/instagram-reels-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/RcimXds0kc0aSKE2A/builds/4PO2K3fc5BcW1CeIL/openapi.json