TikTok Transcript + On-Screen Text (AI-Ready)

Paste TikTok links, get back everything the video says, both spoken and written on screen, as clean JSON with timestamps. Each video also gets a ready-to-paste text block for ChatGPT, Claude, Gemini, or your own pipeline.

$15 per 1,000 videos ($0.015 per video), any length. You pay only for videos that were processed successfully. No login, no cookies, no TikTok account needed.

Works on every TikTok, not only the ones with captions

Many TikTok transcript scrapers return only TikTok's own captions. When a video has no captions, they return nothing, or the run fails. This Actor does not depend on captions: it transcribes the audio itself with AI speech-to-text and reads the text on screen, so you get a result for every public video, captioned or not.

That is also why it costs more than a $1-per-1,000 caption scraper. If every video you need already has captions, a caption scraper is enough. If you are getting empty results or failed runs, this is the fix.

What you can use it for

• Content research and swipe files. Pull the exact hooks, scripts and on-screen text of top TikToks in your niche, then feed them to an AI model to find patterns.
• Hook analysis. Every video gets a hook field with what is said and what is shown in the first 3 seconds, the part that decides whether people keep watching.
• Competitor and brand monitoring. Track what competitors say and show: offers, prices, claims, calls to action.
• AI agents and RAG. Turn short-form video into searchable text. The llm_text field is one block per video, ready for embeddings or a prompt.
• Repurposing. Get the full script of a TikTok (yours or a public one) to rewrite as a post, thread, newsletter or blog.

Why this Actor

	This Actor	Typical TikTok transcript Actor
Spoken transcript with timestamps	Yes, AI speech-to-text (Whisper large-v3-turbo) on every video	Often only TikTok's own auto-captions, empty when the creator has none
Videos without captions	Full transcript	Empty result or failed run
On-screen text (titles, burned-in captions, text stickers, overlays) with timestamps	Yes	No
Overlay vs. caption tagging (text that is not spoken)	Yes	No
Hook (first 3 s, spoken + on-screen)	Yes	No
TikTok watermark	Removed from the on-screen text	n/a
Views, likes, comments, shares	Yes	Varies
Price	$15 / 1,000 videos, any length	AI transcription is often charged per minute

Many TikToks carry half their message, or all of it, as text on screen: lists, facts, punchlines, explainer text over music. A speech-only transcript returns nothing for those. This Actor reads both.

Sample output

From a public National Geographic TikTok with no narration, only text on screen (shortened):

{
  "url": "https://www.tiktok.com/@natgeo/video/7695025994326969614",
  "platform": "tiktok",
  "creator": "National Geographic",
  "creator_handle": "natgeo",
  "published_at": "2026-10-10T13:11:45+00:00",
  "duration_s": 32,
  "views": 15500,
  "likes": 1264,
  "comments": 18,
  "shares": 25,
  "speech_seconds": 6.2,
  "hook": {
    "spoken": "",
    "on_screen": "QUEENS / Grandmother orcas use decades of experience to feed their families."
  },
  "transcript": [],
  "on_screen_text": [
    { "start": 0.5, "end": 4.0, "text": "Grandmother orcas use decades of experience to feed their families.", "position": "top", "kind": "overlay" },
    { "start": 5.0, "end": 8.0, "text": "Orcas are among the very few animals known to experience menopause.", "position": "top", "kind": "overlay" },
    { "start": 21.0, "end": 28.0, "text": "Research found that young orcas with a living grandmother had a better chance of survival.", "position": "top", "kind": "overlay" }
  ],
  "llm_text": "VIDEO: https://www.tiktok.com/@natgeo/video/7695025994326969614\nCREATOR: National Geographic | DURATION: 32s | VIEWS: 15500 ...\nHOOK (first 3s): spoken=\"\" on-screen=\"QUEENS / Grandmother orcas use ...\"\nON-SCREEN TEXT (overlays, not spoken):\n[0:00.5-0:04.0] Grandmother orcas use decades of experience ...",
  "status": "ok"
}

Output fields

Field	Meaning
transcript	Spoken words as timestamped segments (seconds). Empty when the video has no speech.
transcript_text	The transcript as one string.
on_screen_text	Text shown in the video: start/end (seconds), position (top/middle/bottom), kind = caption (repeats the speech) or overlay (text that is not spoken).
hook	What is said and shown in the first 3 seconds.
speech_seconds	Seconds of detected voice. Lets you filter music-only videos.
caption, views, likes, comments, shares, published_at, creator, creator_handle, duration_s	Post metadata.
language	Detected spoken language (ISO code).
llm_text	Everything above as one plain-text block, ready to paste into an AI model.
status	ok, or error with an error message. Failed videos are not charged.

How to use it

1. Paste one or more public TikTok video URLs into Video URLs (tiktok.com/@user/video/..., or vm.tiktok.com/... share links).
2. Click Start.
3. Download the results as JSON, CSV or Excel, or read them through the Apify API, integrations (Make, Zapier, n8n) or the Apify MCP server for AI agents.

Input example:

{
  "urls": [
    "https://www.tiktok.com/@nasa/video/7665075736742530317",
    "https://vm.tiktok.com/XXXXXXXXX/"
  ]
}

A typical TikTok takes 10 to 20 seconds. Videos are processed one after another within a run. For large batches, split the URLs over several runs to process them in parallel.

Reliability

• Tested on 253 public TikToks from 34 creators before launch: 244 of the 247 videos processed (98.8%). The other 6 were photo posts, correctly skipped. Nothing that fails is charged.
• Checked every day. A scheduled run processes live TikToks every morning. If TikTok changes something and it fails, the fix ships within 24 hours.
• Safe on long batches. If Apify moves a run to another server mid-way, it resumes where it stopped. No video is processed or charged twice.

Pricing

• $0.015 per successfully processed video ($15 per 1,000), regardless of video length (tested up to 3 minutes).
• Videos that fail (private, deleted, photo posts, unavailable) are not charged.
• Set Maximum cost per run in the run options to cap your spend. The Actor stops cleanly when the cap is reached.

Settings

Setting	Default	What it does
Video URLs	(required)	Public TikTok video URLs.
Read on-screen text	on	Turn off if you only need the spoken transcript.
Add llm_text field	on	One ready-to-paste text block per video.
Proxy configuration	automatic	Leave empty. The Actor uses Apify datacenter proxy and switches to residential automatically if TikTok blocks a request.

Limitations

• Public videos only. Private accounts, deleted videos and photo posts cannot be processed. They return status: "error" and are not charged.
• On-screen text is most accurate on designed text (titles, captions, text stickers, explainer text). Text that is physically in the scene (signs, jerseys, screens) is read less reliably and partly filtered out. Fast word-by-word captions are sampled, not captured word for word; the spoken transcript covers those words. In rare frames TikTok's moving watermark overlaps a caption and a fragment of it can remain.
• Songs: lyrics may appear in the transcript; pure music returns an empty transcript.
• Instagram or Facebook? Use the sister Actors Instagram Reels Transcript + On-Screen Text and Facebook Reels Transcript + On-Screen Text, same output format.
• Podcasts, audio files or other video links? Use Audio & Video to Text (priced per minute).
• Need frames? Video Frame Extractor returns the key frames of the same links as image URLs, each with its timestamp and the text visible on it ($2 per 1,000 frames).

FAQ

Do I need a TikTok account or cookies? No. The Actor reads only what any logged-out visitor can see.

Which languages are supported? Speech in about 100 languages (Whisper large-v3-turbo). On-screen text is tuned for Latin-script text (English and European languages).

Is this legal? The Actor processes publicly available content and collects no personal data beyond the public post's creator name and handle. You are responsible for how you use the output under the platform's terms and the laws that apply to you (e.g. copyright, GDPR).

Something wrong with a result? Open an issue on the Actor's Issues tab with the video URL. Reliability fixes ship within 24 hours.