TikTok Transcript Scraper — AI Speech-to-Text for Any Video

Turn any TikTok video into text with real AI speech recognition. Paste video links, get back the full spoken transcript plus timestamped sentences as clean JSON — ready for LLMs, RAG pipelines, content research, and subtitle workflows.

This is real ASR, not caption scraping. Most "TikTok transcript" tools only download the captions a creator happened to upload — and fail on the majority of videos that have none. This Actor runs industrial speech recognition on the video's audio track, so it works on any video with speech, captions or not — across English, Chinese, Japanese, Korean, Cantonese, German, French, and Russian.

Unofficial. This Actor is not affiliated with, authorized, or endorsed by TikTok / ByteDance. It is an independent tool that processes publicly available content. Use it in compliance with TikTok's terms and all applicable laws; you are responsible for how you use the retrieved data.

What you get per video

• Full transcript (fullText) — the complete spoken content as one string.
• Timestamped sentences (sentences[]) — each with startMs / endMs, ready for subtitles, deep links, and clip selection.
• Video metadata — author, caption, duration, publish time, play / like / comment / share counts, and cover image URL, so every transcript arrives with its engagement context attached.

Quick start

1. Open the Actor and press Run — the default input works out of the box.
2. Replace the example with your own video links: full URLs (https://www.tiktok.com/@user/video/123…), short share links (https://vt.tiktok.com/XXXX/), or bare video IDs.
3. Optionally set the spoken language (auto-detect by default; a correct hint improves accuracy for Chinese, Japanese, Korean, German, French, and Russian).
4. Collect results from the Dataset tab as JSON / CSV / Excel, or pull them via the Apify API and MCP from your own code.

No proxies, no cookies, no login — everything runs server-side.

Example output

{
  "videoId": "7649091368656194847",
  "videoUrl": "https://www.tiktok.com/@tiktok/video/7649091368656194847",
  "description": "#FilmTok just made first contact with Steven Spielberg…",
  "author": "tiktok",
  "authorName": "TikTok",
  "durationSec": 109.6,
  "playCount": 1240000,
  "diggCount": 98000,
  "language": "en",
  "detectedSpeech": true,
  "sentenceCount": 27,
  "fullText": "Hello, film talk. Well, here I am. He's the most famous and accomplished director of the past century…",
  "sentences": [
    { "text": "Hello, film talk.", "startMs": 380, "endMs": 1690 },
    { "text": "Well, here I am.", "startMs": 1690, "endMs": 3210 }
  ]
}

What people build with it

• LLM & RAG pipelines — index what creators actually say (not just captions) so your assistant can search and cite TikTok content like documents.
• Viral-hook research — pull transcripts of the top videos in your niche and study the exact opening lines, structures, and phrases that earn views.
• Content repurposing — turn TikToks into blog posts, newsletters, and scripts with one LLM step on top of the transcript.
• Brand & compliance monitoring — audit what influencers say about your brand in sponsored content, without watching hours of video.
• Subtitles & translation — timestamped sentences drop straight into SRT/VTT generation and dubbing workflows.
• Trend & meme research — track how a sound or talking point spreads, in the creators' own words.

Pricing & billing

Pay per started transcript minute ($0.025/minute, one-minute minimum). A 50-second video bills one minute; a 70-second video bills two. Failed fetches, deleted videos, photo posts, and failed transcriptions are not charged.

Why this Actor

• Works without captions — real speech recognition on the audio track; caption-scraper alternatives return nothing on most videos.
• Multi-language — auto-detects, with hints for English, Chinese, Japanese, Korean, Cantonese, German, French, and Russian. Chinese recognition quality is best-in-class.
• Engagement context included — every transcript ships with play / like / comment / share counts, so you can rank by performance immediately.
• Direct API, no headless browser — fast, stable runs with nothing to babysit.
• No login, no cookies — we never touch your accounts, so there's no ban risk.
• Structured JSON — export to CSV, Excel, or JSON, or pull straight from the API / MCP.

Tips for better results

• Feed it the winners: use a TikTok search or profile scraper to find the top-performing videos in your niche first, then transcribe just those.
• Sentence timestamps let you deep-link to the exact second a phrase is spoken — handy for review and clip selection.
• detectedSpeech: false flags music-only / no-speech videos so you can filter them out downstream.

FAQ

Do I need an account, cookies, or to log in anywhere? No. The Actor talks to fast, direct HTTP APIs server-side — you just provide video links and run it.

Does it work on videos without captions? Yes — that's the point. It runs real speech recognition on the audio, so captions are never required.

Which languages are supported? Auto-detection works across major languages; explicit hints are available for English, Chinese, Japanese, Korean, German, French, and Russian. Chinese (Mandarin) accuracy is particularly strong.

How long does a video take? Typically 15–40 seconds per video including speech recognition; multiple videos are processed in parallel.

How am I billed? $0.025 per started transcript minute. Videos that can't be fetched or transcribed are not charged.

Can I run it on a schedule or call it from my app? Yes — use Apify Schedules, the REST API, the JavaScript / Python clients, or the MCP server. See the API tab.

Is this affiliated with TikTok? No. It's an independent tool that processes publicly available content. Use it in line with the platform's terms and applicable law.