Instagram & TikTok Video Transcript

Paste Instagram Reel or TikTok links. Get the timestamped transcript, the caption and the public counters of each video as structured data. No login, no cookies, no proxy to set up.

Use cases

Instagram Reel transcript for content research

Read what top creators say without watching 50 Reels. Paste a list of links, search the text for the topics, hooks and claims you care about.

TikTok transcript to text

Turn a TikTok into plain text you can search, quote (with credit), summarize or feed to your own tools. Each transcript comes with the caption, the account and the counters.

Reels to text, for repurposing

Use a Reel or a TikTok as the draft of a blog post, a newsletter or a thread. The full text and the segment list are in the same item, so you can keep the order and the wording.

Subtitles and accessibility

Every transcript comes in segments with start and end times in seconds. Convert them to SRT or VTT with a few lines of code, or keep the text as a readable version for people who cannot listen. The actor returns the segments, not a subtitle file.

Competitor and brand monitoring

Archive what a brand or a competitor publishes, in text form, next to its views, likes and comments. Sort by counters to see which videos work, then read why.

How to use

1. Paste the links. Public Instagram Reel/post or TikTok video links, one per line, up to 100 per run.
2. Press Start. Language is detected for each video. The default settings fit most cases.
3. Get your data. Export the dataset as JSON, CSV or Excel from the run page, or read it through the Apify API.

Input

Field	What it does	Default
urls	Public Instagram Reel/post or TikTok video links, one per line (max 100 per run)	—
transcribeWhenNoSubtitles	Turn off to get only caption, counters and media link	on
whisperModel	base (fast) or small (more accurate, about 3× slower)	base
maxDurationSeconds	Longer videos come back without transcript (30 to 3600)	600

{
  "urls": [
    "https://www.instagram.com/reel/DbOpZRiD2M7/",
    "https://www.tiktok.com/@maverickgpt/video/7661705764901227807"
  ]
}

Output example

One dataset item per link. This is a real TikTok result (caption, text, segments and media link shortened here):

{
  "url": "https://www.tiktok.com/@maverickgpt/video/7661705764901227807",
  "platform": "tiktok",
  "status": "ok",
  "error": null,
  "note": null,
  "account": "maverickgpt",
  "title": "Comment “Skills” and I’ll send you my full list 👇 Claude has over 50,...",
  "caption": "Comment “Skills” and I’ll send you my full list 👇 Claude has over 50,000 skills and most people have never used one. Here are 5 to get you ahead of 99% of people. 1. Stop Slop …",
  "durationSec": 52.69,
  "counts": { "views": 28000, "likes": 1385, "comments": 159, "followers": null },
  "mediaUrl": "https://v19-webapp-prime.tiktok.com/video/…",
  "mediaUrlKind": "muxed",
  "route": "ytdlp",
  "transcript": {
    "source": "whisper-base",
    "language": "en",
    "text": "Clod has over 50,000 skills and most people have never even used one. So here are five to get you ahead of 99% of people. Number one is the stop-slop skill. …",
    "segments": [
      { "start": 0.0, "end": 3.2, "text": "Clod has over 50,000 skills and most people have never even used one." },
      { "start": 3.2, "end": 5.32, "text": "So here are five to get you ahead of 99% of people." },
      { "start": 5.32, "end": 7.04, "text": "Number one is the stop-slop skill." }
    ]
  }
}

What the fields tell you:

• status is ok or error. On error, the reason is in error; the rest is empty.
• note explains an ok item without transcript (no speech detected, post without video).
• transcript.source is whisper-base, whisper-small or none (nothing to transcribe).
• counts holds what the platform shows. A counter it hides comes back as null (here, followers).
• mediaUrl is a temporary link to the video file. Download it soon after the run.

Pricing

You pay per transcription delivered. Links that fail, videos with no speech and runs with transcription turned off are not charged as transcriptions.

Limits

• Public posts only. Private accounts, stories and deleted posts return an error item with the reason. Some Instagram posts that look public can still fail (embed turned off by the owner, or Instagram changed its page).
• Instagram and TikTok. X (Twitter) posts are in beta. YouTube is not supported: YouTube blocks cloud servers, so the run would fail. Use a dedicated YouTube transcript tool.
• Video length. Videos longer than maxDurationSeconds (600 s by default, 3600 s at most) come back without transcript, with caption and counters.
• Posts without video. Image posts and carousels return an item with a note and nothing to transcribe.
• No speech. Music-only videos return an empty transcript (source: none).
• Languages. Any spoken language: the language is detected per video (Whisper covers about 99 languages). French and English are tested in depth; accuracy varies by language. On clips under 10 seconds the detection can be wrong; use small.
• Accuracy. The transcript comes from Whisper. Brand names and jargon can be misheard (the example above writes “Clod” for “Claude”). Use small for better results and check names before you publish.
• Counters. Views, likes and comments appear only when the platform shows them.

FAQ

Do I need to log in or give cookies? No. Paste public links and press Start. There is no proxy to configure.

Which languages does it handle? Any spoken language: it is detected for each video (Whisper covers about 99 languages). French and English are tested in depth; accuracy varies by language, so test a few links before a large run.

Can I get only the caption and the counters? Yes. Turn off transcribeWhenNoSubtitles. You get caption, account, counters and media link, and no transcription is charged.

Can I republish a transcript? Use the tool on content you are allowed to process. Transcripts of other people's videos suit research, accessibility and analysis. Do not republish them as your own.