Instagram scrapers return the caption, likes, comments and video file of each Reel, but not what is said in it. Give this tool the dataset of that run (datasetId) and every Reel in it is transcribed. It uses the video file the scraper already found (videoUrl), so nothing has to be fetched from Instagram again. With Apify’s Connect Actor integration it runs by itself after the scraper.
datasetId: the dataset of an Instagram Reel, post or profile scraper run (pick it in the Input tab); or paste rows in datasetItems.searchTerms finds brands or topics in every transcript, with the time of each mention.Chain both runs from Python:
reels = client.actor("apify/instagram-reel-scraper").call(run_input={"username": ["nasa"], "resultsLimit": 2})
run = client.actor("fguiraud/instagram-reels-transcript-scraper").call(run_input={"datasetId": reels.default_dataset_id})
from apify_client import ApifyClient # pip install apify-client (3.x)
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("fguiraud/instagram-reels-transcript-scraper").call(run_input={
"datasetId": "<DATASET_ID_OF_THE_SCRAPER_RUN>",
"outputs": [
"text"
]
})
for item in client.dataset(run.default_dataset_id).iterate_items():
print(item.get("billedMinutes"), item.get("text", "")[:200])
No Python? Open the Actor page, paste your input in the form and press Start; results export to JSON, CSV or Excel.
Fields from a real run on 2026-11-07 (long values shortened):
{
"status": "ok",
"language": "en",
"durationSeconds": 66.43,
"billedMinutes": 2,
"text": "Mr. President, welcome to Kennedy Space Center. Welcome to Max Power. It is an absolute honor to serve under a president whose vision is igniting a golden age of exploration and energizing the most accomplished space age..."
}
$0.01 per Reel (includes the first minute), then $0.006 per extra minute. The 66-second Reel above was billed $0.016; the Reel without speech was free.
Does it need my Instagram login?
No. It uses the video files from the scraper results, or public Reel links.
Do the video links expire?
The file links in scraper results expire after some hours or days, so transcribe soon after scraping (Connect Actor does it right away). Reel page links also work and do not expire.
Can an AI agent use it?
Yes. It is an MCP server at https://mcp.apify.com/?tools=fguiraud/instagram-reels-transcript-scraper (listed in the official MCP registry), and there is an agent skill for Claude Code, Codex and Cursor. Field-name guesses such as url or urls are accepted.