Instagram Story Transcript (Speech to Text)

The Instagram Story Transcript Actor turns spoken words in public Instagram Story videos into searchable text. Paste Story or Highlight item URLs—no login—and get full transcripts with timed segments and language detection. Use it for influencer monitoring, competitive research, and content archives when brands talk to camera instead of relying on on-screen captions.

For on-screen text, promo codes, and link stickers, use the companion Instagram Story Text Extractor (OCR). This Actor listens to audio only—image Stories are skipped.

---

Key Features

• Speech-to-text: Transcribes voiceover, talking-head, and dialogue in Story videos.
• Timed segments: transcriptSegments with start/end seconds for each spoken phrase.
• Language detection: ISO 639-1 code when speech is present.
• Highlight and live Story URLs: Same URL formats as other Instagram Story Actors.
• No login required: Public Stories and Highlight items only.
• Structured JSON: Export to JSON, CSV, Excel, or pull via Apify API.

---

What data can you extract?

Field	Description
storyUrl	Canonical Instagram Story URL
username	Story owner handle when resolved from metadata
highlightId	Highlight reel id for Highlight item URLs
mediaId	Instagram media id for the Story frame
mediaType	Always video in output (image Stories are not saved)
duration	Length in seconds
language	Spoken language (ISO 639-1) when detected
hasSpeech	true when intelligible speech was transcribed
transcript	Full spoken transcript in the original language
transcriptSegments	Array of { startSec, endSec, text }
scrapedAt	ISO timestamp when the Story was processed

---

Who is it for?

• Brand and influencer analysts archiving what creators say in Stories.
• Compliance and QA teams checking spoken claims in short-form video.
• Researchers building speech corpora from ephemeral Story content.
• Developers scheduling Story transcription on Apify with webhooks.

---

How do I transcribe Instagram Stories?

1. Open the Actor on Apify Console and add start URLs — public Story or Highlight item URLs.
2. Set Max stories (default 5) and enable Apify Proxy (residential recommended) if downloads fail.
3. Run the Actor and open the Dataset tab. Rows appear only for video Stories where speech was detected.
4. Export or call the Apify API for automation.

---

Input

{
  "startUrls": [
    {
      "url": "https://www.instagram.com/stories/highlights/17975319242920589/3713636227774800082/"
    }
  ],
  "maxItems": 5
}

Field	Type	Default	Description
startUrls	request list	—	Public Story or Highlight item URLs
maxItems	integer	5	Maximum stories to process per run
proxyConfiguration	object	Apify Proxy on	Proxy for Instagram media downloads

---

Output example

{
  "storyUrl": "https://www.instagram.com/stories/brand/3456789012345678901/",
  "username": "brand",
  "mediaId": "3456789012345678901",
  "highlightId": null,
  "mediaType": "video",
  "duration": 12.5,
  "language": "en",
  "hasSpeech": true,
  "transcript": "Hey everyone, our sale starts now. Tap the link in our bio.",
  "transcriptSegments": [
    {
      "startSec": 0.5,
      "endSec": 4.2,
      "text": "Hey everyone, our sale starts now."
    },
    {
      "startSec": 4.5,
      "endSec": 7.0,
      "text": "Tap the link in our bio."
    }
  ],
  "scrapedAt": "2026-10-18T12:00:00.000Z"
}

---

How it works

1. Validate URLs — Story and Highlight item patterns are checked.
2. Download media — Guest session download (same stack as the Story Text Extractor).
3. Transcribe video — Gemini analyzes the audio track and returns speech only.
4. Dataset output — One row per video Story with detected speech; no row for image Stories or silent videos.
5. Pay-per-event — story-processed for each video sent to transcription; story-transcript-processed when a transcript is saved.

---

Pricing

This Actor uses pay-per-event billing on Apify plus platform usage (compute, proxy, and AI token usage on your Apify account).

Event	When charged
Story processed	Video Story downloaded and sent for transcription
Story transcript processed	Spoken transcript extracted and saved to the dataset
Actor start	Run start (standard Apify start fee)

Start with a small maxItems (3–5) to estimate cost before scaling.

---

Notes and limitations

• Video only — still image Stories have no spoken track; they are skipped without a dataset row.
• Public Stories only — private accounts are not supported.
• Ephemeral Stories — standard Stories expire after 24 hours; use Highlight URLs for stable tests.
• On-screen text excluded — burned-in captions and stickers are not OCR’d here; use the Text Extractor Actor for that.
• Music and noise — background music may reduce transcription quality; only clear speech is intended.

---

Learn more

• Instagram Story Text Extractor (OCR)
• Apify Instagram Actors
• Apify API docs

Image Credit

Image credit: Instagram