Instagram Reels Transcript API

Turn any Instagram Reel into text with real AI speech recognition.

Instagram has no public transcript feature, and Reels rarely carry captions burned into metadata. This API pulls the Reel's audio and transcribes it with AI speech recognition, returning clean timestamped text for any public Reel.

Great for creator research (what hooks are top Reels using?), brand monitoring, and feeding spoken content into LLM workflows.

Languages: English, Chinese, Japanese, Korean, Spanish, French, German, Russian

Call it from code

The API runs on Apify's platform — one HTTP call starts a run and returns the dataset. Get a free API token by signing up (includes $5/month free usage).

# curl — synchronous run, returns transcript items directly
curl -X POST \
  "https://api.apify.com/v2/acts/ethereal_wool~instagram-reels-transcript-scraper/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"videoUrls": ["https://www.instagram.com/reel/DAcbzHVJEyx/"]}'
# Python
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("ethereal_wool~instagram-reels-transcript-scraper").call(run_input={
    "videoUrls": ["https://www.instagram.com/reel/DAcbzHVJEyx/"],
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item["transcript"])
    for s in item["sentences"]:
        print(s["beginTime"], s["text"])

Pricing

$0.025per minute of video transcribed

No subscription, no minimum. Runs that return nothing are never billed.

Frequently asked questions

What input does it take?

Any public instagram.com/reel/ or /p/ URL, or the bare shortcode (e.g. DAcbzHVJEyx).

Does it work on Reels without captions?

Yes — transcription runs on the audio track itself, so captions are not required.

What does it cost?

$0.025 per minute of video. A typical 30-second Reel costs about $0.0125.

Do I need an Instagram session or cookies?

No — public Reels are fetched server-side with no login required on your part.

What's returned besides text?

Timestamped sentences, plus Reel metadata: author, caption, play count, duration, and thumbnail.

Other platforms