Douyin Transcript API
Turn any Douyin (抖音) video into text — best-in-class Mandarin speech recognition.
Douyin is the Chinese TikTok — and the hardest major platform to get transcripts from. Videos rarely carry subtitles, and western transcription tools handle Mandarin poorly. This API uses a Mandarin-optimized ASR model (Alibaba Paraformer) that leads Chinese speech benchmarks, so the text you get back is actually usable.
Send a Douyin share link (v.douyin.com), a full video URL, or a bare video ID. You get the full transcript, timestamped sentences, and video metadata — author, description, stats — as clean JSON.
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 $5/month free usage).
# curl — synchronous run, returns transcript items directly
curl -X POST \
"https://api.apify.com/v2/acts/ethereal_wool~douyin-transcript-scraper/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
-H "Content-Type: application/json" \
-d '{"videoUrls": ["https://v.douyin.com/iRNBho6u/"]}'# Python
from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("ethereal_wool~douyin-transcript-scraper").call(run_input={
"videoUrls": ["https://v.douyin.com/iRNBho6u/"],
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item["transcript"])
for s in item["sentences"]:
print(s["beginTime"], s["text"])Pricing
No subscription, no minimum. Runs that return nothing are never billed.
Frequently asked questions
Does it handle Douyin share links (口令)?
Yes — paste the v.douyin.com short link from the share sheet and the API resolves it to the video automatically.
How accurate is the Mandarin transcription?
The API uses Alibaba's Paraformer-v2 model, which is optimized for Mandarin and consistently tops Chinese ASR benchmarks — significantly better than Whisper on Chinese short-video audio.
What does it cost?
$0.025 per minute of video. A typical 45-second Douyin video costs about $0.019.
Can I transcribe Douyin videos in bulk?
Yes — pass up to hundreds of URLs per run, or call the API programmatically from your pipeline. Each video is billed by its duration only.
Is login or a Douyin account required?
No. Only public video URLs are needed — no cookies, no account, no browser automation on your side.
Other platforms
TikTok
Turn any TikTok video URL into clean, timestamped text with real AI 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.
Any URL
One endpoint for TikTok, Douyin, Xiaohongshu, Bilibili, and Instagram Reels — paste any link, get text.