Instagram Reel Transcript — AI Video to Text & SRT

Get an Instagram Reel transcript from any public reel, with timestamps, as JSON, SRT or VTT. Instagram Reel Transcript turns Instagram video to text with AI speech-to-text, so it works whether or not the reel has captions. Paste one link or a list of up to 1,000 and get one result per reel: the full text, timed segments, subtitle files laid out for vertical video, optional speaker labels and optional RAG-ready passages for search, summaries, scripts or content research. No Instagram login, cookies or speech-provider API key are needed.

What you get for each Instagram Reel

• Transcript text in text, plus transcript_llm with one line per segment, ready to paste into an LLM prompt.
• Timestamps per segment (t0, t1 in seconds), or per word with timestamps: "word".
• SRT and VTT subtitles in the result and as downloads in the run's key-value store (transcript-000.srt, transcript-000.vtt, numbered by input position).
• Subtitle QA for short video: cues laid out at 28 characters per line by default, with a report of lines that are too long, too fast or too short.
• Readable paragraphs in paragraphs (start_s, end_s, speaker, text) and as transcript-000.txt and transcript-000.md downloads, at no extra charge. See Readable output.
• Speaker labels (S1, S2, …) with diarize: true, for interviews and podcasts clipped into reels.
• RAG passages with source URL and original-video seconds, inline as rag_chunks and as a transcript-000.rag.jsonl download, with exportRag: true.
• Reel duration in duration_s, measured from the downloaded audio.
• Billing per item: every row shows which events were charged.

How to get an Instagram Reel transcript

1. Paste your reel URLs. instagram.com/reel/… links work, and so do the /<user>/reel/…, /reels/…, /p/… and /tv/… forms.
2. Keep the defaults or adjust them. The defaults give segment timestamps and the short-video subtitle layout. Add a language hint, speaker labels or RAG passages if you need them.
3. Set a run budget. In the run options, set a maximum charge for the run. The run stops before work it cannot pay for.
4. Start the run and open the Dataset. Each URL becomes one row. Export it as JSON, CSV or Excel, or read it through the API. Download SRT and VTT files from the run's key-value store.

Input

{
  "urls": ["https://www.instagram.com/reel/DZpQwxqimz2/"],
  "timestamps": "segment",
  "subtitleProfile": "short"
}

Field	What it does
urls	Up to 1,000 public Instagram Reel or video post URLs. Required unless you set datasetId.
datasetId	Read URLs from another run's dataset. See Chain from another Actor.
datasetUrlField, maxItems	The dataset field that holds the URL (detected when empty), and how many rows to read (default 100, at most 1,000).
language	Optional language code such as en, es or pt-BR. Omit it for automatic detection.
timestamps	none (text only: no segments, words, SRT or VTT), segment (default) or word.
subtitleProfile	short (28 characters per line, 0.5–4 s cues) or standard (42 characters per line, 1–7 s cues). Longer segments are split into cues within their time range, and the subtitle QA report is added. When you leave it empty and timestamps are on, short is used. Needs segment or word timestamps, so leave it empty with timestamps: "none".
diarize	Speaker labels. Billed at the speaker-label rate instead of the normal per-minute rate.
exportRag	Adds rag_chunks and a .rag.jsonl download. Needs segment or word timestamps.

Scheduled runs: only new items

Turn on Skip items processed by earlier runs (skipPreviouslyProcessed) and run the Actor on a schedule to get only what is new since the last run.

• The Actor keeps a key-value store named polyglot-processed-instagram in your Apify account, or polyglot-processed-instagram--<memoryKey> when you set Memory name (memoryKey), so separate schedules can keep separate memories. Other Actors keep their own stores, even with the same memoryKey. It records each item after the item is delivered and charged; failed items are tried again next time.
• It applies to every URL in the run: listed ones and dataset rows.
• When nothing is new, the run ends without any charge. Only error rows appear then, for sources or dataset rows that could not be used.
• If the store cannot be opened or read, the run stops before any charge, and the next scheduled run tries again. If an item's record cannot be written, the item is still delivered and the log says so; a later run may process and charge it again.
• Delete the store in Apify Console (Storage → Key-value stores) to start over. Do not run two runs with the same memory at the same time: both would process the same new items.

Chain from another Actor

Run an Instagram scraper such as apify/instagram-reel-scraper first, then paste the dataset ID of that run into Dataset ID (datasetId) to transcribe every one of its Reels:

{ "datasetId": "<dataset ID from the other run>", "maxItems": 200 }

• The Actor reads up to maxItems rows (default 100) with your own run's Apify token and takes each row's URL from webVideoUrl, url, postUrl, videoUrl, inputUrl, link or shortCode, or from the field you name in datasetUrlField.
• Dataset URLs run after any urls you list, in dataset order; a dataset URL that is already in the run is skipped. A run takes at most 1,000 URLs in total.
• A row without a usable URL becomes an error item with its dataset_row index, and it is not charged. Items from the dataset also carry dataset_row, so you can join the results back to the source rows.
• The example link in the URL list is processed and charged too: remove it when you want only the dataset's items.

Output example

A real result from an Apify run on 2026-10-30, trimmed: 4 of 33 segments, and the text, SRT and QA fields shortened.

{
  "url": "https://www.instagram.com/reel/DZpQwxqimz2/",
  "text": "We all know the story of Pompeii, right? The story of Pompeii is a story of death. Or is it? Let's try that again, shall we? …",
  "language": "en",
  "duration_s": 109.06,
  "engine": "groq/whisper-large-v3",
  "segments": [
    { "t0": 0, "t1": 2.3999999, "text": "We all know the story of Pompeii, right?" },
    { "t0": 3.82, "t1": 5.52, "text": "The story of Pompeii" },
    { "t0": 5.52, "t1": 8.54, "text": "is a story of death." },
    { "t0": 10.42, "t1": 11.559999, "text": "Or is it?" }
  ],
  "srt": "1\n00:00:00,000 --> 00:00:02,400\nWe all know the story of\nPompeii, right?\n\n…",
  "subtitle_qa": { "profile": "short", "cue_count": 33, "issue_count": 4, "issues": [{ "cue_number": 5, "code": "reading_speed", "actual": 26.7, "limit": 20 }] },
  "usage": { "minutes": 2, "diarized": false, "platform_fetch": true },
  "billing": {
    "status": "paid",
    "events": [
      { "event": "platform-video-fetch", "requested_count": 1, "charged_count": 1, "state": "confirmed" },
      { "event": "audio-minute", "requested_count": 2, "charged_count": 2, "state": "confirmed" }
    ]
  }
}

This reel is 1 minute 49 seconds long, so it counts as 2 audio minutes. Results also contain vtt, transcript_llm, source_duration_s, start_time_s and end_time_s. A URL that fails returns a row with url and error. Very large results may carry result_record_key instead of inline text; read that key from the run's key-value store.

Readable output

Every transcript row has paragraphs: the transcript in order, grouped into blocks you can read. A paragraph starts at a speaker change, after a pause of 2 seconds or more, and before it would pass 800 characters or 90 seconds. Once it holds 400 characters, the next sentence end closes it. No text is dropped or reordered, and a segment is never split in timed output. Each paragraph is { "start_s", "end_s", "speaker", "text" }; speaker appears only with diarize: true, and with timestamps: "none" there are no times and paragraphs are cut at sentence ends by length alone. Rows without speech have no paragraphs.

The same paragraphs are saved to the run's key-value store, numbered by input position:

• transcript-000.txt: paragraphs separated by blank lines, with S1: style speaker labels.
• transcript-000.md: a title when known, a list with the source URL, language and duration (and the author name when known), then each paragraph with its [mm:ss] (or [h:mm:ss]) start time and bold speaker label.

When a row would pass the Dataset size limit, paragraphs is left out of the row first (the text stays) and the downloads still hold it. Both downloads are free, like SRT and VTT.

How much does an Instagram Reel transcript cost?

Pay per event, with no subscription. These are the Free-plan prices; paid Apify plans get lower per-minute prices. The Pricing tab shows the current prices for your plan.

Event	Price	When
Run setup	$0.005	Once per run.
Instagram Reel download	$0.005	Per reel whose audio was downloaded.
Audio minute	$0.005	Per started minute of video, after transcription succeeds.
Diarized audio minute	$0.010	Per started minute with speaker labels, instead of the audio minute.

Worked examples, without speaker labels:

Reel length	1 URL in a run	100 URLs in a run
1 minute or shorter	$0.005 + $0.005 + $0.005 = $0.015	$0.005 + 100 × $0.010 = $1.005
3 minutes	$0.005 + $0.005 + 3 × $0.005 = $0.025	$0.005 + 100 × $0.020 = $2.005
10 minutes	$0.005 + $0.005 + 10 × $0.005 = $0.060	$0.005 + 100 × $0.055 = $5.505

With speaker labels, a 1-minute reel costs $0.020 alone, and 100 of them cost $0.005 + 100 × $0.015 = $1.505.

• Minutes are rounded up once per reel, and silence counts. A 61-second reel is 2 minutes.
• A reel with no detected speech (only music, silence or noise) returns no_speech: true with empty text and is not charged minutes, up to 30 such minutes per run; after that its minutes are charged. The download fee still applies.
• Put many URLs in one run: the run setup fee is paid once per run, not per reel.
• A failed download is not charged, and neither is a download that is not a playable audio or video file. A successful download stays charged if the transcription fails afterwards.
• You do not know reel lengths in advance, so set maxTotalChargeUsd on the run to cap the spend.
• Apify's own small run-start event is separate and is shown on the Pricing tab.

Use it from the API

Start a run with the Apify API client for JavaScript and read the results:

import { ApifyClient } from 'apify-client'

const client = new ApifyClient({ token: process.env.APIFY_TOKEN })
const run = await client.actor('andronixmd/instagram-reel-transcript').call(
  { urls: ['https://www.instagram.com/reel/DZpQwxqimz2/'] },
  { maxTotalChargeUsd: 0.1 },
)
const { items } = await client.dataset(run.defaultDatasetId).listItems()
for (const item of items) console.log(item.url, item.error ?? item.text)

Or start one run over HTTP:

curl -X POST \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H 'Content-Type: application/json' \
  -d '{"urls":["https://www.instagram.com/reel/DZpQwxqimz2/"]}' \
  'https://api.apify.com/v2/actors/andronixmd~instagram-reel-transcript/runs?maxTotalChargeUsd=0.1'

The Actor also works from n8n and other automation tools through Apify's integrations.

Use it from an AI agent (MCP)

Connect your agent to https://mcp.apify.com. It can find this Actor with search-actors, or call it by name, andronixmd/instagram-reel-transcript, with call-actor. Use fetch-actor-details first for the input schema and pricing. Every call starts a new paid run, so always set callOptions.maxTotalChargeUsd and keep the urls list short:

{ "actor": "andronixmd/instagram-reel-transcript", "input": { "urls": ["https://www.instagram.com/reel/DZpQwxqimz2/"], "timestamps": "segment", "subtitleProfile": "short" }, "callOptions": { "maxTotalChargeUsd": 0.1 } }

call-actor returns the run status and storage IDs, not the results. Read the rows with get-dataset-items and the run's dataset ID. The fields to use are text, paragraphs and error.

With an Apify account, use your API token or MCP OAuth. Without one, an agent can buy a prepaid token from Apify AGI over x402 or MPP and use it as the Bearer token. It starts at $1, the balance is a hard spending cap, and the token expires after 14 days. This is experimental; see agentic payments.

Limitations

• Public reels only. Reels from private accounts, stories, and anything that needs a login are not supported. The Actor uses no accounts or cookies and does not try to get around Instagram's access checks.
• Reel and post URLs only. Profile, story, hashtag, location and search URLs are not accepted. Collect the reel links first, for example with Instagram Reel Scraper or your own list. One URL in a wrong format rejects the whole input before the run starts. /p/… post links are accepted, but a photo-only post has no audio and fails for that item without a download charge.
• Not every public reel will download. Instagram changes how it serves media to logged-out visitors and can refuse some requests, so some URLs return an error row instead of a transcript. Check each row's error and billing fields and retry failed URLs later.
• Spoken audio only. Text drawn into the picture is not read, and the caption the owner wrote under the reel is not included.
• Music-only reels can come back with lyrics, which are billed as speech. A reel detected as having no speech is billed its minutes only after the run's 30 free no-speech minutes.

FAQ

Does it use Instagram's captions? No. It transcribes the audio, so it works whether or not the reel has captions or subtitles.

Which languages does it support? It detects the language automatically, and the supported languages depend on the speech engine. For short clips with music, a language hint such as en, es or de gives better results.

Can I get an SRT file for an Instagram Reel? Yes. With segment or word timestamps (segment is the default), each result contains srt and vtt, and the files are saved in the run's key-value store.

Can I transcribe every reel of a profile? Not directly. The Actor takes reel URLs. Collect the URLs first, then paste them here, up to 1,000 per run.

What happens if a reel fails? You get a row with url and error. A failed download is not charged.

Do you store my transcripts or audio? Results stay in your Apify run storage, under your account's access and retention settings. The audio is sent to the speech-to-text provider that transcribes it. Only submit reels you are allowed to process.

Related Actors

• Instagram Reel Scraper: the caption, hashtags, owner, likes and comment count for the same URLs, without the transcript, for $0.002 per reel. Submit the same URLs to both and join the results on url.
• TikTok Video Transcript: the same transcript output for TikTok videos.
• YouTube Transcript: YouTube captions, with AI speech-to-text when a video has none.
• Audio & Video Transcriber: podcasts, audio and video files and other sites.