Home / Xiaohongshu

Xiaohongshu (RedNote) Transcript API

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

Run it now — free credit includedAPI docs

Xiaohongshu (RedNote) video notes almost never have subtitles, and the platform has no transcript feature at all. This API downloads the note's video stream and runs Mandarin-optimized AI speech recognition on it, returning the spoken content as clean, timestamped text.

It accepts explore/discovery URLs and xhslink.com share links. The response includes the full transcript, sentence timestamps, and note metadata: title, author, like/collect counts.

Languages: Mandarin Chinese (best-in-class), English, and 6 more

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~xiaohongshu-video-transcript-scraper/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"videoUrls": ["https://www.xiaohongshu.com/explore/68a1f2b4000000001d02c8ef"]}'
# Python
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("ethereal_wool~xiaohongshu-video-transcript-scraper").call(run_input={
    "videoUrls": ["https://www.xiaohongshu.com/explore/68a1f2b4000000001d02c8ef"],
})
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

Does it work with xhslink.com share links?

Yes — both full xiaohongshu.com/explore URLs and short xhslink.com share links are accepted.

What about image notes?

The API transcribes video notes. Image-only notes have no audio track, so they are skipped and never billed.

How much does it cost?

$0.025 per minute of video transcribed. A 60-second RedNote video costs $0.025 — no subscription, no minimum.

How accurate is it for Chinese?

It uses Alibaba's Paraformer-v2 ASR, the strongest publicly available Mandarin model — built for exactly this kind of Chinese short-video audio.

Do I need a Xiaohongshu account or cookies?

No. Public note URLs are enough — the API handles everything server-side.

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.

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.

Any URL

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