# Instagram Reel Transcript: Speech-to-Text, Subtitles & Stats (`panix/instagram-reel-transcript`) Actor

Transcribe public Instagram reels to text without login or API key: spoken words, hook, language, timed segments, SRT/VTT subtitles, free English translation, plus plays, likes and caption. For content research, influencer marketing, social listening and AI/RAG pipelines.

- **URL**: https://apify.com/panix/instagram-reel-transcript.md
- **Developed by:** [PANIX AI LAB](https://apify.com/panix) (community)
- **Features:** Limited permissions
- **Stats:** 1 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $8.00 / 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 Reel Transcript: Speech-to-Text, Subtitles & Stats

Turn Instagram reels into text you can search, repurpose or feed to AI. Paste reel links or a username and get the full transcript, the opening hook and the reel's stats.

- **What is actually said in the video**: full transcript, opening hook, word count, language and timed segments, plus optional SRT and VTT subtitles.
- **English translation from 99 languages** at no extra charge.
- **Reel stats and context**: creator, date, likes, comments, caption, hashtags and audio track. No Instagram account, cookies or API key.

**Try it now:** the input is already filled in (two public reels). Click **Start** and the results appear in a table you can export to Excel, CSV or JSON. That example run costs a few cents, which the $5 of free monthly credit on Apify's free plan covers.

**Price:** from **$0.008 per reel** (long reels and high-accuracy mode cost extra), and you pay only for results you get. The full price table is in the Pricing section below.

### Example result

One result, shortened. Every field is described in the Output section below.

```json
{
  "url": "https://www.instagram.com/reel/DehZj9wggt0/",
  "ownerUsername": "natgeo",
  "takenAt": "2026-10-15T19:00:02Z",
  "likes": 59115,
  "comments": 505,
  "durationSeconds": 30.04,
  "language": "en",
  "transcript": "Hudson Bay for a wolf, there are dangers everywhere, but their greatest challenges finding enough food. ...",
  "hook": "Hudson Bay for a wolf, there are dangers everywhere,",
  "wordCount": 56
}
```

### What you get

Turn public Instagram reels into text, without an Instagram account, cookies or an API key. Paste reel links, short codes, profile links or usernames, and get one clean row per reel with **what is actually said in the video**, ready for Excel, Google Sheets, a content tool or an AI pipeline:

- **Transcript**: the full spoken text, the opening line (the hook), word count, detected language and its confidence, seconds of speech.
- **Timed segments**: every sentence with its start and end second, plus optional **SRT and VTT subtitles** and **word-level timestamps**.
- **English translation**: switch it on and reels in Spanish, Hindi, Portuguese, German or any of 99 languages come back in English, at no extra charge.
- **Reel stats and context**: creator, posted date, length, **plays** (for profile runs), likes, comments, caption, hashtags, mentions, collaborators, tagged accounts, the reel's audio track (song or original audio), and links to the thumbnail, video and audio files.
- **Profiles**: give a username and the creator's newest public reels are transcribed for you (up to 12), each with its play count.

You pay only for reels that come back with a transcript. Music-only reels with no speech, photo posts, deleted or private reels and duplicates are free.

### Who uses it

- **Content creators and social media managers**: study what top creators say in their best reels, collect hooks that work, and repurpose reels into blog posts, threads and newsletters.
- **Marketing and brand teams**: monitor competitors' and influencers' reels on a schedule and search what they say about products, prices and offers.
- **Agencies and influencer platforms**: vet creators by what they actually say, check brand mentions in sponsored reels, and report on campaigns.
- **Researchers and journalists**: build datasets of spoken content from news outlets, politicians or public figures, with timestamps for quotes.
- **AI and RAG builders**: feed reel transcripts into vector databases, chatbots and summarizers.
- **Accessibility and localization**: generate subtitles (SRT/VTT) and English translations for videos.

### Why this Instagram transcript scraper

- **No login, no API key, no third-party AI bill.** Speech-to-text runs inside the Actor with OpenAI's open Whisper model, so the price per reel is all you pay.
- **Real speech-to-text, not the caption.** It transcribes the audio. The caption, hashtags and mentions come in separate fields.
- **99 languages with auto-detection** per reel, or pick one language for a whole list.
- **Free English translation** of any language, in the same run.
- **Hook, segments, subtitles and words.** The opening line for hook research, timed segments for clipping, SRT/VTT for captions, and word timestamps for precise editing.
- **Music-only reels are free.** A voice detector checks every reel first. No speech means a free `no_speech` row and no transcription cost.
- **Plays, likes and audio track included** in the same row, so you can rank transcripts by performance.
- **Profiles and links in one box.** Mix reel links, `/p/` and `/tv/` links, bare short codes, profile links and `@usernames`. Chain another Instagram scraper by dataset ID.
- **Pay only for new reels.** Turn on New reels only and a scheduled run skips every reel it transcribed before: no download, no transcription, no charge.
- **Two accuracy levels.** Standard (Whisper base) for clear speech at the lowest price, High accuracy (Whisper small) for accents, noisy audio and less common languages.

#### Coming from another Instagram transcript tool?

| Common problem in this category | How this Actor handles it |
|---|---|
| Music-only or silent reels are still charged | Free `no_speech` row, decided by a voice detector before transcription |
| You need your own OpenAI or other speech-to-text key | Speech-to-text is built in; nothing else to sign up for |
| Translation costs extra per character | English translation is free |
| Only plain text comes back | Timed segments, SRT, VTT and word timestamps |
| Transcript without the reel's numbers | Plays, likes, comments, caption, audio track and posted date in the same row |
| Scheduled runs pay again for old reels | New reels only skips reels already delivered |
| Charged per minute even for a 15-second reel | One flat price per reel up to 90 seconds |
| Only one kind of link accepted | Reel, post and TV links, short codes, profiles, usernames and dataset chaining |

### Input examples

**Reel links** (the example input):

```json
{
  "reels": [
    "https://www.instagram.com/reel/DdUAMWNBktR/",
    "https://www.instagram.com/reel/DehZj9wggt0/"
  ]
}
```

**A creator's newest reels, with subtitles:**

```json
{
  "reels": ["hubermanlab"],
  "maxReelsPerProfile": 12,
  "includeSubtitles": true
}
```

**Spanish and Hindi reels translated to English, high accuracy:**

```json
{
  "reels": ["bbcmundo", "bbchindi"],
  "maxReelsPerProfile": 5,
  "translateToEnglish": true,
  "quality": "high"
}
```

**Daily monitoring of competitors** (run on a schedule; only new reels are transcribed and charged):

```json
{
  "reels": ["@competitor_one", "@competitor_two", "@competitor_three"],
  "newReelsOnly": true,
  "watchlistName": "competitors-daily"
}
```

**Transcribe the reels another Instagram scraper found:**

```json
{
  "datasetId": "<DATASET_ID_FROM_ANOTHER_RUN>"
}
```

#### Input fields

| Field | What it does |
|---|---|
| `reels` | One per line: reel or post link (`/reel/`, `/p/`, `/tv/`), short code (`DdUAMWNBktR`), profile link or username (`nasa`, `@nasa`). Also accepted: `startUrls`, `urls`, `directUrls`, `reelUrls`, `postUrls`, `usernames`, `username` |
| `maxReelsPerProfile` | Newest reels per profile, 1 to 12 (default 12) |
| `skipPinned` | Leave out reels pinned to the top of a profile |
| `datasetId` | Read reel links from another Actor's dataset (`url`, `postUrl`, `inputUrl` or `shortCode` columns) |
| `language` | `auto` (default) or the spoken language for all reels |
| `translateToEnglish` | Deliver the transcript in English (free) |
| `quality` | `standard` (Whisper base) or `high` (Whisper small, extra charge per minute) |
| `includeSegments` | Timed segments (default on) |
| `includeSubtitles` | `srt` and `vtt` fields |
| `includeWordTimestamps` | Every word with start, end and confidence |
| `maxVideoMinutes` | Skip longer videos for free (default 20) |
| `maxResults` | Stop after this many transcripts |
| `newReelsOnly` + `watchlistName` | Skip reels transcribed in earlier runs with the same watchlist name |
| `maxConcurrency` | Reels fetched at the same time (default 6) |
| `proxyConfiguration` | Apify Proxy (default). Profile pages that hit Instagram's login wall are retried on residential IPs automatically |

### Output

Each row has a `status`. Only `transcribed` rows are charged. Free rows: `no_speech` (music or sound only), `not_video` (photo or photo carousel), `too_long`, `no_audio`, and error rows `not_found`, `restricted`, `private`, `no_reels`, `blocked`, `network`. The Output tab has views for Transcripts, Reel stats, Captions & audio, Timed segments, Media files and All rows.

**Transcribed reel** (real output from the example input; segments shortened, file links shortened):

```json
{
  "type": "reel",
  "status": "transcribed",
  "charged": true,
  "url": "https://www.instagram.com/reel/DehZj9wggt0/",
  "shortCode": "DehZj9wggt0",
  "mediaId": "4008597565992995700",
  "productType": "clips",
  "mediaType": "video",
  "ownerUsername": "natgeo",
  "ownerId": "787132",
  "ownerFullName": null,
  "ownerVerified": null,
  "ownerFollowers": null,
  "caption": "Keeping up with a pack of hunting wolves is just another day at the office for @bertiegregory and his team.\n\n#WolvesUpClose with Bertie Gregory premieres Friday, November 6 at 8/7c on National Geographic. Streaming on @DisneyPlus and @hulu.",
  "hashtags": [
    "WolvesUpClose"
  ],
  "mentions": [
    "bertiegregory",
    "DisneyPlus",
    "hulu"
  ],
  "takenAt": "2026-10-15T19:00:02Z",
  "plays": null,
  "likes": 59115,
  "comments": 505,
  "isPinned": null,
  "durationSeconds": 30.04,
  "language": "en",
  "languageProbability": 0.984,
  "translatedToEnglish": false,
  "transcript": "Hudson Bay for a wolf, there are dangers everywhere, but their greatest challenges finding enough food. It's moose hunting season for the wolves. Ready? Moose are dangerous prey. We're in for a wild ride. If we want to film the pack, we've got to keep up. Oh my god. What did you do at work today?",
  "hook": "Hudson Bay for a wolf, there are dangers everywhere,",
  "wordCount": 56,
  "speechSeconds": 23.17,
  "segments": [
    {"start": 0.24, "end": 4.24, "text": "Hudson Bay for a wolf, there are dangers everywhere,"},
    {"start": 4.24, "end": 7.24, "text": "but their greatest challenges finding enough food."}
  ],
  "audioTitle": "Original audio",
  "audioArtist": "natgeo",
  "isOriginalAudio": true,
  "hasAudio": true,
  "coauthors": [
    "bertiegregory",
    "natgeoanimals"
  ],
  "taggedUsers": [
    "natgeoanimals",
    "bertiegregory"
  ],
  "locationName": null,
  "carouselVideoPosition": null,
  "thumbnailUrl": "https://scontent-arn2-1.cdninstagram.com/v/t51.82787-15/849098148_1870...?oe=...",
  "videoUrl": "https://scontent-arn2-1.cdninstagram.com/o1/v/t2/f2/m86/AQPmzWFyFbdQEU...?oe=...",
  "audioUrl": "https://scontent-arn2-1.cdninstagram.com/o1/v/t2/f2/m78/AQMigN4zZ5qE3Z...?oe=...",
  "mediaUrlsExpireAt": "2026-11-08T23:32:31Z",
  "transcriptionModel": "whisper-base",
  "chargedExtraMinutes": 0,
  "chargedHighAccuracyMinutes": 0,
  "statusMessage": null,
  "input": "https://www.instagram.com/reel/DehZj9wggt0/",
  "inputType": "reel",
  "foundVia": null,
  "scrapedAt": "2026-11-07T15:13:36Z",
  "schemaVersion": 1
}
```

- Rows from a profile also have `plays`, `isPinned`, `ownerFullName`, `ownerVerified` and `ownerFollowers`, and `foundVia` is `profile:<username>`.
- `hook` is the text spoken in the first seconds: the opening line viewers hear.
- With `includeSubtitles`, `srt` and `vtt` hold complete subtitle files. With `includeWordTimestamps`, `words` lists every word with `start`, `end` and `probability`.
- `videoUrl`, `audioUrl` and `thumbnailUrl` are Instagram's signed file links. They stop working at `mediaUrlsExpireAt` (one to two days later), so download files soon if you need them.
- Whisper writes what it hears. Names, brands and slang can be misspelled, and the Standard model is weaker on heavy accents and noisy audio; use High accuracy for those.

**Free row** examples: `{"status": "no_speech", "charged": false, "statusMessage": "no speech was heard (music or sound only)", ...}` (with all the reel's stats) and `{"type": "error", "status": "not_found", "input": "https://www.instagram.com/reel/DAAAAAAAAAA/", "error": "the reel does not exist, was deleted or its account is private"}`.

Each run also saves `SUMMARY` in its key-value store: totals, charged events, rows per status, errors per code, audio minutes and request statistics.

### Pricing

Pay per event, no monthly rental, no speech-to-text bill on the side. Your price depends on your Apify plan:

| Event | Free plan | Starter (Bronze) | Scale (Silver) | Business (Gold) and up |
|---|---|---|---|---|
| Reel transcript (up to 90 seconds) | $12.00 / 1,000 | $10.00 / 1,000 | $9.00 / 1,000 | $8.00 / 1,000 |
| Extra minute (each started minute after the first 90 seconds) | $0.005 | $0.004 | $0.0036 | $0.0032 |
| High accuracy (only with `quality: high`, per started minute of video) | $0.012 | $0.010 | $0.009 | $0.008 |
| Actor start | $0.001 per run per GB of memory (the default 4 GB uses four) | | | |

- Included in the reel price: timed segments, subtitles, word timestamps, English translation, stats, caption and audio track.
- Free: music-only reels, photo posts, too-long videos, deleted, private or hidden reels, profiles without reels, duplicates and reels skipped by New reels only.
- Examples on Starter: 1,000 reels of up to 90 seconds = **$10.00**. A 2-minute reel = $0.014. A 3-minute reel = $0.018. A 45-second reel with High accuracy = $0.020.
- Set a spending limit on the run (Run options → Max cost per run). The Actor checks the cost of each reel before it transcribes it and stops cleanly at the limit.

### FAQ

**Do I need an Instagram account, cookies or an OpenAI key?** No. The Actor reads Instagram's public reel pages, the same ones anyone sees without logging in, and runs speech-to-text itself.

**Is this the caption or the spoken words?** The spoken words, transcribed from the reel's audio. The caption is in its own field.

**Which languages work?** Whisper recognizes 99 languages. English, Spanish, Portuguese, French, German, Italian and other widely spoken languages work well on Standard; for Hindi, Arabic, Urdu, Tagalog and other languages, or for mixed-language speech, use High accuracy.

**How accurate is it?** On clear speech, Standard gets most words right; High accuracy is noticeably better on accents, background music and names. Check names and numbers before you publish quotes.

**What happens with music-only reels?** A voice detector checks the audio first. If nobody speaks, you get a free `no_speech` row with the reel's stats.

**Why do profiles give at most 12 reels?** Instagram shows visitors who are not logged in a profile's 12 newest reels. For more, paste the reel links you want or chain another scraper's dataset.

**Why is `plays` empty for some rows?** Instagram shows play counts on a profile's Reels tab, not on the reel page. Rows found through a profile have plays; rows from pasted links have likes and comments.

**How fast is it?** At the default 4 GB, a 30-second reel takes a few seconds. More memory adds CPU cores and speeds up big batches.

**Is it legal to scrape Instagram?** The Actor collects publicly available content only and never logs in. Transcripts can contain what people say about themselves or others, so process them in line with laws such as the GDPR and Instagram's terms for your use case. If unsure, ask a lawyer.

### Limits

- Public reels and video posts only. Private accounts, stories, highlights, lives and age-restricted reels are not available without a login (free rows say why).
- Up to 12 newest reels per profile. No hashtag or keyword search.
- In a carousel post, the first video is transcribed.
- On-screen text (text burned into the video) is not read; only speech.
- Instagram can change its site. If something breaks, open an issue on the Issues tab and it gets fixed.

### Use it from code and automation tools

**Python** (`pip install apify-client`):

```python
from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("panix/instagram-reel-transcript").call(run_input={
    "reels": ["https://www.instagram.com/reel/DdUAMWNBktR/", "natgeo"],
    "maxReelsPerProfile": 5,
})
for row in client.dataset(run.default_dataset_id).iterate_items():
    if row["status"] == "transcribed":
        print(row["ownerUsername"], row["plays"], row["hook"])
        print(row["transcript"][:300])
```

**JavaScript** (`npm install apify-client`):

```javascript
import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('panix/instagram-reel-transcript').call({
    reels: ['@hubermanlab'],
    includeSubtitles: true,
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items.filter((r) => r.status === 'transcribed').map((r) => `${r.shortCode}: ${r.hook}`));
```

**HTTP API** (run and get the rows in one call):

```bash
curl -X POST "https://api.apify.com/v2/acts/panix~instagram-reel-transcript/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{"reels": ["https://www.instagram.com/reel/DdUAMWNBktR/"]}'
```

**n8n, Make and Zapier**: use the Apify app or node, action "Run Actor", Actor `panix/instagram-reel-transcript`, paste the input JSON, then "Get dataset items" to send transcripts to Google Sheets, Notion, Airtable, Slack or an AI step. A common flow: a daily schedule with New reels only → new competitor reels → summarize each transcript with an AI step → post to Slack.

**AI agents (MCP)**: the Actor works with Apify's MCP server, so Claude, ChatGPT and other agents can call it as a tool to read what an Instagram reel says.

*Not affiliated with, endorsed by or sponsored by Instagram or Meta Platforms, Inc. Instagram is a trademark of Meta Platforms, Inc.*

# Actor input Schema

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

One per line, mixed freely: a reel or video post link (instagram.com/reel/..., /p/..., /tv/...), a bare short code (DdUAMWNBktR), a profile link (instagram.com/nasa) or a username (nasa or @nasa). For a profile, its newest public reels are transcribed (see Reels per profile).

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

For each profile or username: how many of its newest reels to transcribe (1 to 12). Instagram shows logged-out visitors a profile's 12 newest reels, so 12 is the most per profile.

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

Leave out the reels a creator pinned to the top of their Reels tab (often old reels), so you get only the newest ones.

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

Optional: the ID of a dataset from another Instagram scraper run. Every row's url, postUrl, inputUrl or shortCode is read and transcribed (up to 5,000 rows).

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

Leave on Auto-detect: each reel's language is detected on its own (99 languages). Pick a language only if all your reels are in it; this skips detection and avoids rare wrong guesses on short or noisy clips.

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

Deliver the transcript in English, whatever language is spoken (the detected language is still reported). No extra charge. Best with High accuracy for languages other than Spanish, French, German, Portuguese and Italian.

## `quality` (type: `string`):

Standard uses the Whisper base model: fast and good for clear speech in English and other major languages. High uses the Whisper small model: noticeably better on accents, noisy audio, music under speech, names and less common languages, about three times slower, and adds the high-accuracy charge per reel.

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

Add the transcript split into timed segments (start and end second, text). Good for clipping, captions and quoting.

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

Add ready-made subtitle files as text in the srt and vtt fields.

## `includeWordTimestamps` (type: `boolean`):

Add every word with its start and end second and a confidence score (for karaoke-style captions or precise cuts). Makes transcription a little slower.

## `maxVideoMinutes` (type: `integer`):

Videos longer than this are not transcribed and not charged (they get a free row with status too_long). Reels are up to 3 minutes; older video posts can be much longer. Every started minute after the first 3 adds the extra-minute charge.

## `maxResults` (type: `integer`):

Stop after this many transcribed reels. Leave empty for no limit. You can also cap the cost with the run's maximum charge.

## `newReelsOnly` (type: `boolean`):

For scheduled runs: remember every reel transcribed under the watchlist name and skip it next time, so each run downloads, transcribes and charges only reels that are new since the last run.

## `watchlistName` (type: `string`):

Keeps separate memories for separate lists (letters, digits, - and \_). Runs with the same name share one memory.

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

How many reels are fetched at the same time while others are transcribed. The default suits most runs; transcription speed depends on the run's memory (each 4 GB adds a CPU core).

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

Instagram pages are read through Apify Proxy. The default (automatic datacenter proxy) works and costs nothing extra; switch to residential only if your runs report blocked pages.

## Actor input object example

```json
{
  "reels": [
    "https://www.instagram.com/reel/DdUAMWNBktR/",
    "https://www.instagram.com/reel/DehZj9wggt0/"
  ],
  "maxReelsPerProfile": 12,
  "skipPinned": false,
  "language": "auto",
  "translateToEnglish": false,
  "quality": "standard",
  "includeSegments": true,
  "includeSubtitles": false,
  "includeWordTimestamps": false,
  "maxVideoMinutes": 20,
  "newReelsOnly": false,
  "watchlistName": "default",
  "maxConcurrency": 6,
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}
```

# Actor output Schema

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

All rows. Filter by status: transcribed rows are charged; music-only reels, photo posts, missing reels and other free rows say why in statusMessage or error.

## `summary` (type: `string`):

Totals, charged events, rows per status, errors per code, audio minutes, speech-model CPU time and request statistics.

# 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/DdUAMWNBktR/",
        "https://www.instagram.com/reel/DehZj9wggt0/"
    ],
    "proxyConfiguration": {
        "useApifyProxy": true
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("panix/instagram-reel-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 = {
    "reels": [
        "https://www.instagram.com/reel/DdUAMWNBktR/",
        "https://www.instagram.com/reel/DehZj9wggt0/",
    ],
    "proxyConfiguration": { "useApifyProxy": True },
}

# Run the Actor and wait for it to finish
run = client.actor("panix/instagram-reel-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 '{
  "reels": [
    "https://www.instagram.com/reel/DdUAMWNBktR/",
    "https://www.instagram.com/reel/DehZj9wggt0/"
  ],
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}' |
apify call panix/instagram-reel-transcript --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,panix/instagram-reel-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/Jmx91hrhtNavuG1p9/builds/7bwcKqMZoAwBwMnCu/openapi.json
