Instagram Reels Transcript avatar

Instagram Reels Transcript

Under maintenance

Pricing

Pay per event

Go to Apify Store
Instagram Reels Transcript

Instagram Reels Transcript

Under maintenance

Transcribe public Instagram Reels and video posts to text, SRT and VTT. Language detection, caption, metrics, optional AI summary. No login.

Pricing

Pay per event

Rating

0.0

(0)

Developer

Márcio Makoto Nakamura

Márcio Makoto Nakamura

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

a day ago

Last modified

Security

Limited permissions

Share

Turn any public Instagram Reel into text. Paste Reel, video post or profile links and get the full transcript, ready-to-use SRT and VTT subtitles, the detected language, the post caption, public metrics and the author. No Instagram login. No cookies. No account to risk.

This actor does one thing: Instagram video to text. It is not a multi-platform scraper, so every field is tuned for Instagram Reels.

What you get for every video

FieldExample
transcriptFull text of what is said
segments, srt, vttTimed lines and subtitle files, ready for CapCut, Premiere, YouTube or Instagram
languagept, en, es... detected automatically
caption, hashtags, mentionsWhat the author wrote under the post
metricsPublic views, likes and comments
durationSec, postedAt, typeLength, publish date, Reel or video post
authorUsername, name, followers, verified flag
musicSong and artist, or "Original audio"
aiSummary (optional)Hook, 1-2 sentence summary, key points, topics, call to action
status, errorMessagesuccess, no_speech, unavailable, video_unavailable... so a bad link never breaks your batch

Who uses it

  • Content creators. Study why a competitor's Reel works: read its hook word for word, then write yours. Turn your own Reels into blog posts, newsletters and captions.
  • Agencies and social teams. Add subtitles to client videos in minutes, check brand mentions in what influencers actually say (not only in captions), and keep a searchable archive of campaign Reels.
  • Researchers and analysts. Collect the spoken content of public accounts for trend, media or discourse analysis, with timestamps you can cite.
  • AI repurposing and agents. Feed transcripts to an LLM to produce threads, scripts, summaries or training data. Works as a tool for AI agents (see below).

How to use it

  1. Click Try for free and paste links into Reel, post or profile links. One per line.
  2. Leave the language on Auto-detect.
  3. Click Start. Results appear in the Transcripts tab. Download as JSON, CSV or Excel.

Accepted inputs: instagram.com/reel/..., instagram.com/p/... (video posts), instagram.com/tv/..., instagram.com/username and @username. For a profile the actor transcribes the videos among its newest public posts (usually the latest 6 to 12 that Instagram shows publicly). Older videos need their own links.

Input example

{
"urls": [
"https://www.instagram.com/reel/DfX5dqygwky/",
"@natgeo"
],
"maxVideosPerProfile": 3,
"language": "auto",
"includeTimestamps": true,
"aiSummary": true
}

Output example

{
"url": "https://www.instagram.com/reel/DfX5dqygwky/",
"status": "success",
"language": "en",
"transcript": "A spectacle of nature. The northern lights can take on a variety of colors.",
"wordCount": 14,
"segments": [{ "start": 0, "end": 4.2, "text": "A spectacle of nature." }],
"srt": "1\n00:00:00,000 --> 00:00:04,200\nA spectacle of nature.\n",
"vtt": "WEBVTT\n\n00:00:00.000 --> 00:00:04.200\nA spectacle of nature.\n",
"caption": "A spectacle of nature, the northern lights can take on a variety of colors.",
"hashtags": ["SecretsOfThe..."],
"author": { "username": "natgeo", "isVerified": true, "followers": 268203474 },
"metrics": { "views": 91997, "likes": 25347, "comments": 77 },
"durationSec": 14.57,
"transcriptSource": "speech-to-text",
"aiSummary": {
"hook": "A spectacle of nature.",
"summary": "The northern lights appear in many colors.",
"keyPoints": ["Auroras vary in color"],
"topics": ["northern lights", "nature"],
"callToAction": null
}
}

(Illustrative. Real values come from the video.)

Pricing

You pay only for what you get, per event:

EventWhen it is chargedPrice
video-transcribedOnce per video with speech, plus once more for each extra 3 minutes of video (a 40-second Reel = 1 event, a 7-minute video = 3)$0.007
ai-summaryOnce per video when you turn on AI summary and hook$0.002

Not charged: private or removed posts, image posts, Reels whose video file Instagram does not share, videos with no speech (music only or silence), videos over your length limit, invalid links, and runs that fail.

Set Max cost per run in the run options and the actor stops cleanly when it is reached; everything transcribed so far is kept.

Free Apify plan

On the free plan you can transcribe 10 videos per day (counted across all your runs, resetting at midnight UTC), each up to 3 minutes. The run's status message always tells you how many are left, and the log explains how to lift the limit. Any paid Apify plan removes both limits.

Use it from AI agents (MCP)

Every Apify actor is available to AI assistants through the Apify MCP server. Add https://mcp.apify.com?actors=the_coder_senior/instagram-reels-transcript to Claude, Cursor, VS Code or any MCP client, and an agent can ask: "Transcribe this Reel and write three hooks in the same style."

The input is small and every field has a plain-language description, so agents fill it correctly on the first try. Output is flat JSON with stable field names. Run it from code too:

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('the_coder_senior/instagram-reels-transcript').call({
urls: ['https://www.instagram.com/reel/DfX5dqygwky/'],
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0].transcript);

Good to know

  • Public content only. The actor reads what Instagram shows to anyone without an account. Private accounts, stories and removed posts are reported as unavailable.
  • Speech, not captions. Instagram does not publish spoken-word captions for Reels, so audio is converted to text with Whisper large-v3-turbo. Accuracy is highest on clear speech in major languages; music-heavy, noisy or heavily accented audio can contain errors. Check anything you will quote.
  • Songs are transcribed too. If a Reel has sung vocals, the lyrics come back as text (Whisper may mishear them). Reels with only instrumental music or ambient sound return no_speech and are not charged.
  • Some Reels cannot be read. Instagram does not share the video file of some public Reels (often ones using restricted music). Those return video_unavailable and are not charged.
  • Very short remarks may be missed. A clip of 6+ seconds where only one or two words are detected is treated as no_speech.
  • Burned-in text is not read. Words that only appear on screen as text overlays are not part of the transcript. The caption is returned separately.
  • Rate limits. The actor spaces out its requests and retries politely. Keep Parallel videos low.
  • Your responsibility. Transcripts are the work of their creators. Respect copyright, platform terms and privacy law (GDPR, LGPD, CCPA) when you store or republish them.
  • This actor is not affiliated with or endorsed by Instagram or Meta.

Support

Something not working on a link? Open an issue in the Issues tab with the link and the status you got. A fix usually ships within days.