Instagram Video Transcript

Affiliate disclosure: Apify links on this page may include referral parameters. If you sign up through one of these links, TrueFetch may earn a commission from Apify at no extra cost to you. Pricing, features, and Actor access are unaffected.

Instagram Video Transcript converts one public Instagram Reel or video post into detected-language text, timestamped segments, source metadata, and an optional translated transcript for content analysis and reuse.

• The required input is one Instagram video URL; profile pages, playlists, uploads, and cross-platform links are outside this Actor's scope.
• Each successful run returns one normalized Dataset record with 22 fields, including transcript text, segment timestamps, creator details, and available engagement metrics.
• The optional translation selector contains 133 target languages and is charged only when every segment is translated successfully.
• The media pipeline verifies a local audio stream and real media duration before transcription, and rejects input files larger than 8 GB.

Run a one-result test · View API

A smallest useful FREE-tier test uses one short public Reel. It bills one $0.40 transcript event, the default 8 GB start charge of $0.008, and variable Actor usage. A completed translation adds $0.12.

What does Instagram Video Transcript do?

Instagram Video Transcript turns spoken audio from one public Instagram Reel or video post into structured text. The result includes a full transcript, detected language, and ordered segments with HH:MM:SS.mmm start and end timestamps. When Instagram exposes source details, the same record can also include the caption or title, creator identifiers, duration, thumbnail, publishing time, audio attribution, and engagement counts.

Select a translate target to receive a timestamp-aligned second transcript. The original remains in transcript; the translation appears in translation.

It is not a profile crawler, Story archiver, bulk collector, live-caption service, video downloader, or subtitle generator. Each run processes one public Instagram media URL.

How do I run Instagram Video Transcript?

1. Open Instagram Video Transcript on Apify.
2. Copy the canonical URL of one public Instagram Reel or video post and paste it into Video URL.
3. Optionally select one Translate target. Leave it empty to return only the detected-language transcript.
4. Click Start and wait for the run to finish.
5. Review the single record in the default Dataset before exporting or connecting downstream automation.

Start with a short Reel that contains clear speech. The current input schema pre-fills this public Instagram Reel URL:

{
  "video_url": "https://www.instagram.com/reels/DVNBl6iDoT0/",
  "translate": "spanish"
}

What data does Instagram Video Transcript return?

The Actor writes one successful result to the default Dataset. It uses the following 22-field contract. Source fields are nullable because Instagram may omit or restrict individual values.

Group	Dataset fields	Meaning
Processing	processor, processed_at	Actor URL and UTC processing time
Post	platform, title, description, thumbnail, published_at	Instagram identity, caption-like text, image, and publishing time
Creator	author, author_id, author_url	Account details exposed for the media
Media	duration, audio_title, audio_artist	Length and source-provided audio attribution
Engagement	view_count, like_count, shares_count, dislike_count, comment_count	Counts that Instagram exposes to the extraction path
Labels	categories, tags	Source-provided classifications when available
Speech	transcript, translation	Original timestamped transcript and optional translated version

The following abbreviated JSON mirrors the current Dataset schema examples for that Reel. Its duration value is 0, the documented sentinel when source duration is unavailable.

{
  "processor": "https://apify.com/truefetch/instagram-video-transcript?fpr=aiagentapi",
  "processed_at": "2026-07-21T14:14:27+00:00",
  "platform": "Instagram",
  "title": "Video by concept_bytes",
  "author": "Concept Bytes",
  "duration": 0,
  "transcript": {
    "language": "English",
    "text": "I built a timer that can play chess. It's a robot clock I made to teach me how to play.",
    "segments": [
      {
        "start": "00:00:00.000",
        "end": "00:00:09.730",
        "text": "I built a timer that can play chess. It's a robot clock I made to teach me how to play. Because I have"
      }
    ]
  },
  "translation": {
    "language": "Spanish",
    "text": "Construí un temporizador que puede jugar al ajedrez.",
    "segments": [
      {
        "start": "00:00:00.000",
        "end": "00:00:09.730",
        "text": "Construí un temporizador que puede jugar al ajedrez."
      }
    ]
  }
}

The Dataset does not include a status field, source video file, SRT/VTT file, summary, confidence score, speaker identity, or word-level timeline.

What inputs can I configure?

Input	Type	Required	Behavior
video_url	string	Yes	One public Instagram Reel or video-post URL.
translate	string enum	No	One of 133 target-language values. Empty means no translation.

video_url must resolve to downloadable public Instagram media. The Actor does not accept credentials, uploads, profiles, date filters, or URL lists.

Translation values are lowercase language names such as spanish, japanese, or chinese (simplified). Translation does not alter the original transcript.

What platforms and markets does Instagram Video Transcript cover?

This Instagram-only Actor accepts canonical public Reel and video-post URLs, including /reel/, /reels/, and video-bearing /p/ links.

Stories, private accounts, deleted posts, region-restricted media, and login-gated content are unsupported. Public availability can change after publication.

Speech language is detected from audio. Generated translation still needs review for names, slang, and context-specific wording.

Process only content you are authorized to use and review the official Instagram Terms of Use for your use case.

Why use Instagram Video Transcript?

Verified capability	Practical benefit
Instagram-specific URL validation	Reject unrelated platform links before a paid transcription workflow proceeds.
Transcript text and timestamped segments	Search the spoken message while retaining time ranges for review or clipping decisions.
Instagram metadata in the same record	Keep creator, caption, duration, thumbnail, and available engagement context beside the speech.
Optional timestamp-preserving translation	Review one Reel in another language without losing the original transcript.
One normalized record per run	Connect a predictable object to editorial, research, monitoring, or AI workflows.

Instagram can change what a public URL exposes, and speech recognition can mishear names, accents, overlapping voices, music-heavy audio, or specialized vocabulary. Review quotations and high-stakes findings.

Who is Instagram Video Transcript for?

The Actor is designed for developers, social media teams, researchers, journalists, creator analysts, localization teams, and AI-workflow builders who already have a specific public Reel URL. Useful scenarios include extracting a spoken hook for editorial analysis, making interview clips searchable, comparing the spoken message with the post caption, preparing a draft translation for review, and supplying time-aligned text to a downstream summarizer.

It is not the right product for users who need an entire profile, many URLs in one run, comments, downloaded media, embedded on-screen text recognition, guaranteed legal transcripts, or live social listening. Choose an Instagram post or profile scraper when metadata breadth matters more than spoken audio.

How can I use Instagram Video Transcript through the API or MCP?

The public Actor identifier is truefetch/instagram-video-transcript. Use the asynchronous Actor endpoint for longer media or workflows that should not hold one HTTP connection open. Apify documents that synchronous Dataset responses can return HTTP 408 after a long wait even when a run continues.

curl -L "https://api.apify.com/v2/actors/truefetch~instagram-video-transcript/run-sync-get-dataset-items" \
  -H "Authorization: Bearer YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://www.instagram.com/reels/DVNBl6iDoT0/",
    "translate": "spanish"
  }'

Apify's hosted MCP server can expose only this Actor to a compatible client:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=truefetch/instagram-video-transcript",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

After connecting, ask the client to call truefetch/instagram-video-transcript with {"video_url":"https://www.instagram.com/reels/DVNBl6iDoT0/","translate":"spanish"}. Verify authentication and tool selection with the official Apify MCP server guide, and use the Actor API page for generated client examples.

How much does Instagram Video Transcript cost?

Instagram Video Transcript uses pay-per-event pricing. Confirm the live pricing page before a large or scheduled workload because Store prices can change.

Billed event	FREE	BRONZE	SILVER	GOLD	PLATINUM	DIAMOND	Billing unit
Actor start	$0.001	$0.001	$0.001	$0.001	$0.001	$0.001	One event per allocated GB, minimum one
Actor usage	$0.00001	$0.00001	$0.00001	$0.00001	$0.00001	$0.00001	Runtime, proxy, and storage usage unit
Transcript	$0.40000	$0.38667	$0.37333	$0.36000	$0.36000	$0.36000	One successful timestamped transcript
Translation	$0.12000	$0.11600	$0.11200	$0.10800	$0.10800	$0.10800	One complete translated transcript when requested

Smallest FREE-tier example: the default 8 GB run creates eight start events, so $0.001 × 8 + $0.40000 = $0.408, plus variable Actor usage. A completed Spanish translation makes the fixed-event subtotal $0.528, plus usage. Use Apify's maxTotalChargeUsd run option when a scheduled integration needs a hard spending ceiling.

How does Instagram Video Transcript compare with alternatives?

Option	Best fit	Trade-off
Instagram Video Transcript	One known Instagram media URL, spoken text, timestamps, and available source context	One item per run; no profiles, comments, media file, or speaker labels
Instagram post scraper	Captions, comments, hashtags, and post analytics	Spoken audio transcription may be absent or secondary
Universal video-to-text Actor	Mixed platforms or uploaded media	Less narrowly guided Instagram input experience
Manual transcription	Sensitive quotes that require human judgment	More time and coordination for timestamps and translation

Use this Actor when spoken content is the primary data. Choose Instagram Post Scraper for post-centric metadata, Video To Text for uploaded media or other platforms, and Best Video Downloader when the required deliverable is the media file.

What are the limits and troubleshooting steps?

Symptom or limit	What it means	Next step
The Actor rejects the platform	The URL does not resolve as supported Instagram media	Copy the canonical Reel or video-post URL from Instagram
Video information cannot be retrieved	The post is private, expired, deleted, restricted, or temporarily blocked	Confirm the URL opens publicly and retry later with the canonical link
The media has no usable speech	Audio is absent, silent, music-only, or too unclear for speech detection	Test a short Reel with clear dialogue
Metadata is empty or duration is 0	Instagram did not expose that creator, audio, timing, publishing, or engagement value	Treat source fields as optional; do not infer missing values
Translation is absent	One or more transcript segments did not translate completely	Keep the original transcript and retry; incomplete translation is not charged
A synchronous API call returns HTTP 408	The HTTP response exceeded Apify's documented synchronous wait behavior	Start asynchronously, poll the run, then read the Dataset

Segment boundaries are ordered but are not word-level timestamps. Do not post a private token, private Reel, or confidential content in an issue. Share the run ID, the smallest public reproduction URL, the expected behavior, and the visible error.

Frequently asked questions

Can Instagram Video Transcript process a private Reel?

No. The public input has no credential or cookie field. Use only media that the Actor can access from its canonical public URL.

Does it process Stories or an entire profile?

No. The supported public contract is one Reel or video-post URL per run. Story archival and profile crawling are not promised.

Does it use Instagram's existing captions?

The output is generated from audible speech. It does not return an existing Instagram caption file, on-screen text layer, SRT, or VTT file.

What happens when a Reel contains only music?

The run can report that no speech was detected. Use a Reel with spoken dialogue when transcript text is required.

Why are views, likes, or audio attribution empty?

Those values depend on what Instagram exposes for that exact post. The Dataset keeps them nullable rather than inventing a value.

Is translation billed if one segment fails?

No. A translation event is charged only after a complete translated transcript is attached to the result.

Can I use the segment timestamps as subtitles?

They are useful time ranges for downstream processing, but the Actor does not create a subtitle file or guarantee word-level alignment. Review them before publication.

Can I schedule the same URL repeatedly?

Yes. Apify schedules can rerun saved input. Each successful run is independently billed, and source metadata may change between runs.

Related TrueFetch Actors

• Instagram Post Scraper focuses on the post, caption, creator, and engagement context when spoken-audio transcription is not the only goal.
• Video To Text accepts uploaded media and public URLs from many platforms when an Instagram-only input contract is too narrow.
• Best Video Downloader is the better fit when the expected output is a downloadable media file rather than transcript data.

Support and last updated

• Actor page and documentation
• API reference and generated clients
• Issues
• TrueFetch community
• Direct support

Local schema, metadata pricing, and documentation links were last verified on July 21, 2026. Instagram availability is external and may change after that date.

Run a one-result test · View API