Home / Any URL

Universal Video Transcript API

One endpoint for TikTok, Douyin, Xiaohongshu, Bilibili, and Instagram Reels — paste any link, get text.

Run it now — free credit includedAPI docs

One API, five platforms. Paste any mix of TikTok, Douyin, Xiaohongshu (RedNote), Bilibili, and Instagram Reels URLs and get back uniform, timestamped transcripts — same JSON shape regardless of source platform.

This is the endpoint to build on when your input URLs come from users or scraped lists and you don't control which platform they point at. Platform detection, link resolution (short links included), audio extraction, and Mandarin/English ASR are all handled for you.

Languages: English, Chinese (Mandarin), Japanese, Korean, Spanish, French, German, Russian

Call it from code

The API runs on Apify's platform — one HTTP call starts a run and returns the dataset. Get a free API token by signing up (includes $5/month free usage).

# curl — synchronous run, returns transcript items directly
curl -X POST \
  "https://api.apify.com/v2/acts/ethereal_wool~any-url-transcript/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"videoUrls": ["https://www.tiktok.com/@tiktok/video/7649091368656194847"]}'
# Python
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("ethereal_wool~any-url-transcript").call(run_input={
    "videoUrls": ["https://www.tiktok.com/@tiktok/video/7649091368656194847"],
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item["transcript"])
    for s in item["sentences"]:
        print(s["beginTime"], s["text"])

Pricing

$0.025per minute of video transcribed

No subscription, no minimum. Runs that return nothing are never billed.

Frequently asked questions

Which platforms are supported?

TikTok, Douyin (抖音), Xiaohongshu (小红书/RedNote), Bilibili (B站), and Instagram Reels — including each platform's short/share link formats.

Is the output the same across platforms?

Yes — every item has the same shape: url, platform, author, title/description, durationSec, transcript, and timestamped sentences. No per-platform parsing on your side.

How is it billed?

$0.025 per minute of video transcribed, identical across platforms. A run that transcribes nothing bills nothing.

Can I mix platforms in one request?

Yes — pass any mix of URLs in a single run; each is routed to the right platform adapter automatically.

What languages does the speech recognition support?

8 languages with automatic detection; Mandarin Chinese accuracy is best-in-class (Alibaba Paraformer-v2).

Other platforms

TikTok

Turn any TikTok video URL into clean, timestamped text with real AI speech recognition.

Douyin (抖音)

Turn any Douyin (抖音) video into text — best-in-class Mandarin speech recognition.

Xiaohongshu (小红书 / RedNote)

Turn any 小红书 video note into text — Mandarin-optimized speech recognition.

Bilibili (B站)

Turn any B站 video into text — handles long-form content, BV/av IDs, and b23.tv links.

Instagram Reels

Turn any Instagram Reel into text with real AI speech recognition.

YouTube

Fetch YouTube transcripts at scale — by URL, video ID, or search keyword.