Any URL Transcript — Video to Text for TikTok, Reels, Douyin, B站 & RedNote

One Actor, every short-video platform. Paste video links from TikTok, Instagram Reels, Douyin (抖音), Bilibili (B站), or Xiaohongshu (小红书 / RedNote) — in any mix — and get back the full spoken transcript plus timestamped sentences as clean JSON. Real AI speech recognition, ready for LLMs, RAG pipelines, content research, and subtitle workflows.

This is real ASR, not caption scraping. Most "transcript" tools only download captions a creator happened to upload — and most short videos have none. This Actor runs industrial speech recognition on each video's audio track, so it works on any video with speech, captions or not. Chinese (Mandarin) recognition is best-in-class; English, Cantonese, Japanese, and Korean are supported too.

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

Supported platforms

Platform	Accepted links
TikTok	tiktok.com/@user/video/…, vm.tiktok.com/…, vt.tiktok.com/…
Douyin 抖音	douyin.com/video/…, v.douyin.com/…, pasted share text
Instagram Reels	instagram.com/reel/…, /p/…, /tv/…
Bilibili B站	bilibili.com/video/BV…, b23.tv/…, bare BV ids
Xiaohongshu 小红书	xiaohongshu.com/explore/…, xhslink.com/…

The Actor auto-detects the platform per URL — mix them freely in one run.

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.
• Platform + metadata — platform, author, title/caption, duration, publish time, play / like / comment / share counts where the platform provides them.

Quick start

1. Open the Actor and press Run — the default input works out of the box.
2. Replace the examples with your own links from any supported platform.
3. Language defaults to Auto-detect; set it explicitly for single-language batches to improve accuracy (Chinese is best-in-class).
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

{
  "platform": "tiktok",
  "videoId": "7405073368414408965",
  "videoUrl": "https://www.tiktok.com/@khaby.lame/video/7405073368414408965",
  "author": "khaby.lame",
  "durationSec": 18.2,
  "playCount": 24500000,
  "likeCount": 2900000,
  "language": "auto",
  "detectedSpeech": true,
  "sentenceCount": 4,
  "fullText": "You don't need an expensive gadget for this…",
  "sentences": [
    { "text": "You don't need an expensive gadget for this.", "startMs": 410, "endMs": 2750 }
  ]
}

What people build with it

• Cross-platform content research — compare what creators say about the same topic on TikTok, Reels, and the Chinese platforms, in one dataset.
• Viral-hook mining — transcribe the winners across platforms and study the exact opening lines that earn views everywhere.
• Agent & workflow integration — one endpoint for "video URL → text" means your agent doesn't need to care which platform a link came from.
• LLM & RAG pipelines — build multilingual short-video speech corpora with engagement scores attached.
• Subtitles & translation — timestamped sentences drop straight into SRT/VTT generation and dubbing workflows.

Pricing & billing

Pay per started transcript minute ($0.025/minute, one-minute minimum) on every supported platform. Failed fetches, deleted videos, image posts, unsupported URLs, videos over your duration cap, and failed transcriptions are not charged.

Why this Actor

• One input for five platforms — no more wiring a separate scraper per platform into your pipeline.
• Real speech recognition — works without captions; Chinese (Mandarin) accuracy is best-in-class, where Western tools struggle most.
• Cheapest stream selection — smallest encode per platform, audio-only on Bilibili, so runs stay fast.
• 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: find the top-performing videos in your niche first (search / profile scrapers), then transcribe just those.
• Single-language batch? Set the language explicitly — it noticeably improves accuracy over Auto.
• detectedSpeech: false flags music-only / no-speech videos so you can filter them out downstream.
• Long Bilibili videos: raise maxDurationMinutes (up to 240) for lectures — audio-only downloads keep even those runs quick.

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-detect, Chinese (best-in-class), Cantonese, English, Japanese, and Korean.

How am I billed? $0.025 per started transcript minute on every platform. 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 the platforms? No. It's an independent tool that processes publicly available content. Use it in line with each platform's terms and applicable law.