Instagram Reels Transcript Extractor — Audio to Text

Turn any public Instagram reel into text: the full spoken transcript with timestamps, on-screen text overlays, and the reel's caption and engagement stats — no login, no cookies.

What you get

• Full spoken transcript of the reel, verbatim, in 100+ languages with automatic language detection
• Timestamped segments (MM:SS) for subtitles, quoting, and content repurposing
• On-screen text overlays — hooks, captions, and titles burned into the video
• Reel metadata: username, caption, posted date, duration, like/comment/play counts
• Export to JSON, CSV, Excel, or Google Sheets directly from the Apify console

Use cases

• Content research — study viral reel hooks, scripts, and structures at scale
• Content repurposing — turn reels into blog posts, newsletters, and captions
• Competitor analysis — monitor what topics and phrases competitors use
• Accessibility — generate transcripts and subtitles for your own reels
• Trend mining — extract what creators in a niche are actually saying

How to use

1. Paste one or more Reel URLs (up to 50 per run)
2. Leave Language on auto, or set an ISO code like en / es if you know the spoken language
3. Run the actor — one record per reel appears in the Dataset tab

Output format

{
  "inputUrl": "https://www.instagram.com/reel/ABC123/",
  "shortcode": "ABC123",
  "postUrl": "https://www.instagram.com/reel/ABC123/",
  "username": "instagram",
  "caption": "a moment for the fluffy boots…",
  "takenAt": "2026-08-05T16:02:11.000Z",
  "durationSeconds": 15,
  "likeCount": 152340,
  "commentCount": 1834,
  "playCount": 2450000,
  "language": "en",
  "transcript": "Okay so these are the boots everyone keeps asking about…",
  "segments": [{ "start": "00:00", "text": "Okay so these are the boots…" }],
  "onScreenText": ["the boots everyone is talking about", "link in bio"]
}

FAQ

Does it work on any reel? Any public reel or video post. Private accounts and deleted posts return a clear per-item error without stopping the run.

What about reels with no speech? You still get the on-screen text overlays and full metadata; the transcript comes back empty.

How accurate is it? Transcription uses a state-of-the-art speech model with automatic language detection — accuracy is comparable to professional subtitle services.