Instagram Transcript Scraper - Reels & Video: MCP config, n8n workflow and API

{
  "videoUrls": [
    "https://www.instagram.com/p/Dew5IIlNfMW/"
  ],
  "maxPosts_per_username": 0,
  "transcriptionMethod": "auto",
  "whisperModel": "base",
  "includeSegments": false
}

---
name: instagram-transcript-scraper-reels-and-video
description: "Instagram video to text: paste many reel, post or IGTV links and get each transcript with creator, caption and likes. Reads Instagram captions or uses AI speech-to-text in 29 languages, with optional timestamps per phrase. Export to JSON, CSV or Excel for subtitles and research. Runs the Apify Actor dataspryva/instagram-transcript-scraper-reels-and-video. Use when the user needs Instagram data with fields such as status, postUrl, profileUrl, shortCode, videoIndex, pk and an Apify token is available."
compatibility: "Needs network access, curl, and an APIFY_TOKEN environment variable. Runs are billed to the token owner's Apify account."
metadata:
  actor: "dataspryva/instagram-transcript-scraper-reels-and-video"
  store-url: "https://apify.com/dataspryva/instagram-transcript-scraper-reels-and-video"
---

# Instagram Transcript Scraper - Reels & Video

Use this skill to fetch Instagram data with the Apify Actor `dataspryva/instagram-transcript-scraper-reels-and-video` and work with the returned rows.

## Before running

1. Check that `APIFY_TOKEN` is set in the environment. Never print it or write it to a file.
2. Build `input.json` from the user's request using the fields below. Keep limits small for a first run.
3. Confirm the search terms or URLs with the user if the request is ambiguous.

## Input fields

| Field | Type | Meaning |
| --- | --- | --- |
| `videoUrls` | array | List of Instagram video or reel URLs to transcribe. Supports /p/, /reel/, and /tv/ formats. Provide this, usernames, or both. |
| `usernames` | array | Usernames whose newest posts should be checked for videos. Each entry can be a username (with or without @) or a profile link such as https://www.instagram.com/natgeo/. |
| `maxPosts_per_username` | integer | How many of each username's newest posts to check (after the date and pinned-post filters below). Every video among them is transcribed (each video of a carousel on its own); a post without a video gets a record with the status not_a_video. |
| `transcriptionMethod` | one of `auto`, `native`, `whisper` | How to extract transcripts. 'auto' tries native Instagram captions first, then falls back to Whisper AI. 'native' only uses Instagram captions. 'whisper' always uses AI speech-to-text. |
| `whisperModel` | one of `tiny`, `base`, `small` | Whisper AI model size. Larger models are more accurate but use more memory and time. Only used when transcription method involves Whisper. |
| `includeSegments` | boolean | When enabled, the output will include a 'segments' array with per-segment timestamps and text alongside the full transcript. Each segment represents a distinct phrase with start/end times in seconds. |

Example `input.json` (the Actor's published prefill):

```json
{
  "videoUrls": [
    "https://www.instagram.com/p/Dew5IIlNfMW/"
  ],
  "maxPosts_per_username": 0,
  "transcriptionMethod": "auto",
  "whisperModel": "base",
  "includeSegments": false
}
```

## Run

```bash
curl -sS -X POST "https://api.apify.com/v2/acts/dataspryva~instagram-transcript-scraper-reels-and-video/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d @input.json > results.json
```

The call waits for the run to finish and returns the dataset items as a JSON array. If the run needs more than 300 seconds the API answers with HTTP 408; then start the run with `POST /v2/acts/dataspryva~instagram-transcript-scraper-reels-and-video/runs`, poll `GET /v2/actor-runs/{runId}` until `SUCCEEDED`, and read `GET /v2/datasets/{defaultDatasetId}/items`.

## Output

Each item is one record. Published fields include: `status`, `postUrl`, `profileUrl`, `shortCode`, `videoIndex`, `pk`, `id`, `postDescription`, `thumbnailUrl`, `videoUrl`, `audioUrl`, `pubDate`, `likeCount`, `commentCount`, `userId`, `userName`, `userFullName`, `avatarUri`, `fullText`, `transcriptionMethod`.

Summarise what was found, cite the record URLs when present, and say how many items came back. Do not invent values for empty fields.