Instagram Transcript Scraper: Reels Transcript API

Turn Instagram Reels into text. Paste reel links, creator usernames or another scraper's dataset and get one row per reel: everything said in it, in the language it was spoken, with timed segments, the first 3 seconds of speech and the reel's caption, views, likes and posting date. Need subtitles? Switch on SRT or WebVTT. You pay $3 per 1,000 reels ($0.003 each, first 60 seconds included), and music-only or silent reels are free.

The input form is pre-filled with two reels, so the quickest way to try it is to click Start (about $0.006).

What do you get for each reel?

Field	What it means
status	ok = transcript delivered (charged). no_speech = music, sound effects or silence (free). Anything else = couldn't be read (free)
transcript	Everything said in the reel, in its original language. Never translated
segments	Each spoken line with start and end in seconds
hook3s	The words spoken in the first 3 seconds
subtitles	The transcript as SRT or WebVTT text, if you switch it on
language, speech	Spoken language (en, es, pt, hi...) and how clear the speech was (clear, faint, none)
reelUrl, creator, caption, hashtags, postedAt	The reel and its public details
views, likes, comments, durationSeconds	Public numbers when the reel was read
audio	Sound title and artist, and whether it is the creator's original audio
charged, chargedUsd, errorCode, errorMessage	Exactly what the row cost, and why a reel has no transcript

What can you use Instagram transcripts for?

• Hook research and swipe files: collect the first 3 seconds of hundreds of reels in a niche and see which openings get views.
• Script and UGC research: read how creators and brands structure a 30-second pitch before you write your own.
• Competitor monitoring: schedule it daily on a list of accounts and get the text of every new reel.
• Repurposing: turn your own reels into captions, blog posts, newsletters or subtitles.
• AI pipelines and RAG: clean text with timestamps, ready for search, summaries and chatbots.

Why use this Instagram transcript scraper?

• You pay for transcripts, not for tries. No start fee and no charge per row. Music-only reels, faint speech, copyright-blocked, deleted or failed reels cost nothing.
• Honest about music. Speech models invent "Thank you." over songs. We detect that and return a free no_speech row instead of junk text. Quiet dialogue under music comes back as a free faint transcript.
• The original language. Each reel is transcribed in the language it is spoken in (English, Spanish, Portuguese, French, Hindi, Korean and 90+ more). You can force a language when auto-detection guesses wrong.
• Hooks, subtitles and timestamps built in. hook3s, timed segments and SRT/WebVTT at no extra cost.
• No login, no cookies, no Instagram account. It reads the public reel only.

How much does it cost?

Reel	Price
Up to 60 seconds	$0.003
90 seconds	$0.005
3 minutes	$0.007
Music only, silent or faint speech	free
Deleted, private, copyright-blocked, too long or failed	free

That is $3 per 1,000 reels for typical reels; longer videos add $0.002 per extra minute. Your spending limit is always respected: reels past it come back as free skipped rows. On the Apify free plan you get 100 reels a month with this Actor. To keep free rows fair for everyone, a run stops after 50 free rows or twice as many free rows as transcripts, whichever is more; a normal mix of reels never reaches it.

How do I transcribe an Instagram Reel?

Paste the link under Reel links and click Start. Reel, post, tv and share links all work, one per line, up to 1,000 per run. Each reel takes a few seconds, and 6 run at a time on the default memory, so 100 reels take about 7 minutes.

How do I get a creator's new reels every day?

Add usernames or profile links under Creators. The Actor reads each creator's newest posts (about the latest 6) and transcribes the videos. Put it on an Apify schedule once a day to catch every new reel. For a creator's older reels, list them with an Instagram profile scraper first and use the dataset option below.

How do I transcribe reels found by another scraper?

Put that run's dataset ID under Dataset ID. The Actor reads the url or shortCode of each row, removes duplicates and transcribes each reel once.

How do I get SRT subtitles for an Instagram Reel?

Set Subtitle file text to SRT or WebVTT. Each row then has a subtitles field you can save as a .srt or .vtt file.

Input example

{
  "reelUrls": ["https://www.instagram.com/reel/DfIfj7vS3qt/"],
  "creators": ["hubermanlab"],
  "subtitleFormat": "srt"
}

Output example

Shortened, with illustrative text:

{
  "status": "ok",
  "reelUrl": "https://www.instagram.com/reel/EXAMPLE123/",
  "creator": "examplecreator",
  "postedAt": "2026-10-31T13:38:34+00:00",
  "durationSeconds": 41.5,
  "views": 54144,
  "likes": 3120,
  "language": "en",
  "speech": "clear",
  "hook3s": "Stop scrolling, here is",
  "transcript": "Stop scrolling, here is the one habit that fixed my mornings...",
  "segments": [
    {"start": 0.0, "end": 2.4, "text": "Stop scrolling,"},
    {"start": 2.4, "end": 6.1, "text": "here is the one habit that fixed my mornings"}
  ],
  "wordCount": 112,
  "charged": true,
  "chargedUsd": 0.003
}

How do I use Instagram transcripts with an AI agent or LLM?

Add the Actor to any MCP client (Claude, Cursor, VS Code and others) with https://mcp.apify.com?tools=meridianlabs/instagram-reels-transcript, then ask in plain words, for example: "Transcribe the newest reels from these three creators and list the hooks they open with."

From code, call the run-sync endpoint and read the rows straight back:

curl -X POST "https://api.apify.com/v2/acts/meridianlabs~instagram-reels-transcript/run-sync-get-dataset-items?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"reelUrls": ["https://www.instagram.com/reel/DfIfj7vS3qt/"]}'

It also works from n8n, Make, Zapier, Google Sheets and Apify schedules.

Error codes (all free)

Code	Meaning
NO_SPEECH	Music, sound effects, silence, or only faint speech
COPYRIGHT_BLOCKED	Instagram keeps this reel's video in the app because of its music
NOT_FOUND	Deleted, private, or a wrong link
NOT_A_VIDEO	A photo or carousel post
NO_VIDEO_LINK	Instagram didn't provide the video file this time
TOO_LONG	Over 10 minutes
BLOCKED	Instagram didn't answer this time. We never work around a block; run it again later
CREATOR_NOT_FOUND	Unknown or private creator
INVALID_INPUT	Not an Instagram reel or post link
SPENDING_LIMIT, RUN_TIME_LIMIT, FREE_PLAN_LIMIT, FREE_ROW_LIMIT	Skipped because a limit was reached

FAQ

Which languages does it transcribe?

Any of the 90+ languages Whisper large-v3-turbo understands. The spoken language is detected per reel and the transcript stays in it. Set Spoken language if a reel mixes languages or detection guesses wrong.

Do I need an Instagram account or cookies?

No. It reads only what a logged-out visitor can see. Private accounts can't be transcribed.

Why do some reels come back as unavailable?

Instagram doesn't release some reels with licensed music outside its app. Those rows are free.

Can it translate transcripts?

No. You get the original words. Translate them afterwards with any tool or LLM if you need to.

Is it legal to transcribe Instagram Reels?

The Actor reads public reels only, logged out, and keeps no video files. Transcripts are someone else's words: use them for research, analysis, accessibility or your own content, and respect creators' rights and Instagram's terms. You are responsible for how you use the data.

Does it collect personal data?

It returns the creator's username with each reel and nothing else about people: no followers, comments, bios or contact details. Emails and phone numbers spoken in a reel are masked by default. To ask for a removal, write to admin@meridianlabssoftware.com.

What happens if a run times out or restarts?

Reels already delivered are not fetched or charged again after a restart. When the time limit gets close, unstarted reels become free skipped rows and the run still succeeds.

More from Meridian Labs

• AI Visibility Tracker: whether ChatGPT, Perplexity, Gemini and Claude name your brand, with share of voice vs competitors. From $0.008 per answer.
• YouTube Transcript API & Scraper: transcripts of YouTube videos and Shorts in their original language. $3 per 1,000 transcripts.
• Facebook Ads Library Scraper: every ad a competitor runs on Facebook and Instagram. $0.10 per 1,000 ads.
• Keyword Search Volume & CPC API + Google Trends: search volume, CPC and trends for keyword lists. From $5 per 1,000 keywords.
• Backlink Checker: referring domains, backlinks and domain rank for up to 1,000 domains a run.
• Google Jobs Scraper: Salaries, Apply Links & API: every job Google Jobs shows for a search, up to 200, with full descriptions, every apply link and salary normalised to yearly and hourly. $1.50 per 1,000 jobs.

Support

Found a reel that comes back wrong? Open an issue on the Issues tab with the link. We read every one.

If this saved you time, a rating helps others find it; if something's off, open an issue and we'll fix it fast.