Instagram Reels Transcript - Reel to Text, No Login

Turn Instagram Reels into text. This Actor transcribes the spoken audio of public Instagram Reels with AI speech-to-text, so it works even when a Reel has no captions or subtitles. Paste Reel URLs, get clean transcripts as JSON, CSV or Excel, or pull them straight into your app through the API. No Instagram login needed.

What can this Instagram Reels transcript tool do?

• Transcribe Instagram Reels and video posts to text, including Reels without captions
• Return the full transcript, word count and audio duration for every Reel
• Optionally return timestamped segments and the detected spoken language
• Process many Reels in one run, in parallel, and skip duplicate URLs automatically
• Stop exactly at the spending limit you set for a run
• Charge nothing for Reels that cannot be fetched (private, removed, blocked) or that have no audio track

Who uses Instagram Reel to text?

• Content and social media teams repurposing Reels into blog posts, threads and captions
• Marketers and researchers analysing what competitors and creators say in their Reels
• Developers and AI agents feeding Reel transcripts into summarisers, classifiers, search indexes or RAG pipelines
• Accessibility work that needs a text version of short videos

How to transcribe Instagram Reels

1. Add one or more public Reel URLs, for example https://www.instagram.com/reel/CDUMkliABpa/. Links to /reel/, /reels/ and video posts /p/ are accepted; tracking parameters are ignored.
2. Optional: set the spoken language (for example en, es, pt, ko) to improve accuracy on very short or noisy clips.
3. Optional: turn on Include segment timestamps to get start and end times for each spoken segment.
4. Click Start. Each Reel appears in the dataset as soon as it is done.

Input example

{
  "urls": [
    "https://www.instagram.com/reel/CDUMkliABpa/",
    "https://www.instagram.com/reels/CDUMkliABpa/?igsh=abc"
  ],
  "language": "en",
  "includeTimestamps": false,
  "maxDurationMinutes": 10
}

The second URL is the same Reel, so it is processed and billed once.

Output example

Real output from a test run:

{
  "url": "https://www.instagram.com/reel/CDUMkliABpa/",
  "platform": "instagram",
  "videoId": "CDUMkliABpa",
  "status": "succeeded",
  "durationSec": 13.5,
  "text": "Like a woman, ooh. Like a woman, ooh.",
  "wordCount": 8,
  "model": "gpt-4o-mini-transcribe",
  "charged": true,
  "errorCode": null
}

Field	Description
status	succeeded, no_speech (music only), no_audio, failed or skipped
text	Full transcript of the spoken audio
wordCount, durationSec	Transcript length and audio length in seconds
language, segments	Present when timestamps are enabled
author, caption	Reel metadata when Instagram provides it
errorCode, errorMessage	Why a Reel was not transcribed
charged	Whether the item was billed

How much does it cost to transcribe Instagram Reels?

Pay per event, no subscription:

Event	Price
Reel transcribed (first minute of audio)	$0.01
Each additional started minute	$0.01

1,000 Reels of up to one minute cost $10; longer Reels add $0.01 per extra started minute.

Not charged: invalid URLs, private or removed Reels, Reels Instagram blocks, and Reels without an audio track. A Reel that contains only music is transcribed and returned as no_speech; it is billed like any transcription, because the audio was processed.

Set a maximum charge for the run and the Actor will never exceed it: once the budget is reached, the remaining Reels are returned as skipped without being processed.

Use it from the API, integrations and AI agents

Run it like any Apify Actor through the API, schedules, webhooks, Make, Zapier or n8n. Example with the Python client:

from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("<username>/instagram-reels-transcript").call(
    run_input={"urls": ["https://www.instagram.com/reel/CDUMkliABpa/"]}
)
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item["status"], item["text"])

AI agents connected to the Apify MCP server can find and call this Actor directly.

Limits

• Public Reels only. Private accounts and login-only content are not supported.
• Audio longer than Maximum minutes per video (default 10) is cut at that length.
• Instagram occasionally rate-limits requests. The Actor retries through the configured proxy before reporting a failure, and failed Reels are not billed.

FAQ

Does it read on-screen text or captions?

No. It transcribes what is spoken in the audio, which is why it works on Reels that have no captions.

What happens with background music?

Speech is transcribed. A Reel with music and no speech returns no_speech.

Which languages are supported?

The speech-to-text model handles most widely spoken languages. Setting the language explicitly helps on short clips.

Can I use the transcripts with my own AI model?

Yes. The output is plain JSON designed to feed your own summariser, classifier, search index or LLM.

Is it legal to transcribe Instagram Reels?

The Actor only processes publicly available Reels and does not log in. You are responsible for how you use the data; check Instagram's terms and the laws that apply to you.