Douyin Transcripts Scraper: Video to Text, SRT & English avatar

Douyin Transcripts Scraper: Video to Text, SRT & English

Pricing

from $1.20 / 1,000 videos

Go to Apify Store
Douyin Transcripts Scraper: Video to Text, SRT & English

Douyin Transcripts Scraper: Video to Text, SRT & English

Douyin (抖音) video transcripts without login: paste video or share links and get what is said, word for word, with timestamps, SRT subtitles, the opening line and an optional English translation, plus each video's likes, comments, shares, saves, author and music. Batch many links per run.

Pricing

from $1.20 / 1,000 videos

Rating

0.0

(0)

Developer

Zaiq

Zaiq

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

a day ago

Last modified

Share

Douyin Transcripts Scraper: Douyin video to text, with timestamps, SRT and English (抖音, no login)

Turn Douyin (抖音) videos into text: paste video links or share links and get what is said, word for word, in the language spoken, with timestamps for every sentence, a ready SRT subtitle file, the opening line (the hook) and, if you want it, an English translation (or 18 other languages). Each row also carries the video's likes, comments, shares, saves, caption, hashtags, author and music.

Put as many links as you like in one run: videos up to 10 minutes are written down, silent and failed ones are free, and nothing needs a Douyin account. Built for content research, China market and trend analysis, subtitling and translation, AI datasets and AI agents.

What you get

FieldWhat it holds
Transcripttranscript (word for word, with punctuation; Mandarin in Simplified characters), transcriptLanguage, hook (the opening line: the first 3 seconds of speech, to the end of its sentence) and hookStartSeconds
Timestamps (on by default)segments (start and end in seconds, text) and srt (the subtitle file as text)
Translation (optional)translation, translationLanguage
VideoawemeId, text (caption), createdAt, durationSeconds, likes, comments, shares, saves, hashtags, series, cover, videoUrl, url
Author and musicauthor (name, Douyin ID, bio, posts, link), music (title, author)
SUMMARYwhat each link returned, notes, minutes written down and what was charged

What people use it for

  • Content research: what the top Douyin creators in a niche actually say, and how they open
  • Hooks and scripts: the opening lines of videos that went viral, side by side
  • Subtitles: an SRT file per video, in Chinese and, translated, in English
  • China market research: what Chinese creators say about a product, brand or category
  • Translation: Chinese videos in English, without listening to them
  • AI datasets and RAG: clean Chinese speech text with timestamps
  • AI agents: Douyin video to text inside any workflow, paid per minute

How to use it

  1. Paste Douyin video links (douyin.com/video/..., v.douyin.com share links, or a whole share text), one per line.
  2. Keep Timestamps on for segments and SRT, and pick a language under Translate transcripts to if you want one.
  3. Click Start, then download the table (JSON, CSV, Excel) or read it through the API.

Input

FieldExampleNotes
Video linkshttps://www.douyin.com/video/<id>Links, share links, share texts or ids; many per run
TranscriptsonOff: only the videos' details
Timestamps and subtitlesonSegments and an SRT file; no extra charge
Translate transcripts toEnglishOr 18 other languages; no extra charge from this Actor

Output

Each result is one row in the run's dataset (download it as JSON, CSV, Excel, XML or HTML, or read it through the API). An example row (values shortened):

{
"awemeId": "7692394891321576714",
"url": "https://www.douyin.com/video/7692394891321576714",
"hook": "阿离。",
"hookStartSeconds": 3.4,
"transcript": "阿离。吓到了吧?你没事吧?怎么到这的?不知道,眼睛一闭一睁,就听到你叫我了。走,回家。再买身衣服。人跑了!把人抓回来!谁…",
"transcriptLanguage": "zh",
"segments": [
{
"start": 3.4,
"end": 4.5,
"text": "阿离。"
},
{
"start": 7.7,
"end": 9.2,
"text": "吓到了吧?"
},
{
"start": 10.9,
"end": 13.0,
"text": "你没事吧?怎么到这的?"
}
],
"srt": "1\n00:00:03,400 --> 00:00:04,500\n阿离。\n\n2\n00:00:07,700 --> 00:00:09,200\n吓到了吧?\n…",
"translation": "A-Li. Were you scared? Are you okay? How did you get here? I don't know, I just closed my eyes and opened them, and then…",
"translationLanguage": "English",
"text": "《鬼才谈恋爱·归处》 没积分了弹尽粮绝了朋友们,这集只做一个承上启下的剧情,祝大家假期快乐!",
"createdAt": "2026-10-03T11:01:02Z",
"durationSeconds": 193,
"likes": 6594,
"comments": 224,
"shares": 319,
"saves": 1526,
"hashtags": [
"LibTV",
"LibTV创作者成长计划",
"AI短片"
],
"author": {
"name": "示例创作者",
"douyinId": "…",
"posts": 6
},
"series": "鬼才谈恋爱"
}

A record named SUMMARY in the run's key-value store says what each link returned, with notes (for example a deleted video), how many minutes were written down and what was charged. The example row is from a run on 17 October 2026 (creator name removed): a 193-second video, written down in 53 timed segments with its English translation; 1 video and 4 transcript minutes were charged.

Pricing

  • $0.0015 per video with its details ($1.50 per 1,000)
  • $0.005 per started minute of transcript, with timestamps, SRT, the opening line and the translation
  • Silent videos, failed transcripts and videos that are deleted, private or withheld by Douyin are free
  • The AI model that writes the speech down (Google's Gemini Flash) is billed by Apify at its exact cost: about $0.004 a minute with timestamps and translation on paid Apify plans (measured 17 October 2026); Apify charges free-plan accounts 10 times that

What typical jobs cost at the list price:

JobCost
One 1-minute video with transcript$0.0065
100 one-minute videos with transcripts$0.65
100 three-minute videos with transcripts$1.65
1,000 videos, details only$1.50

On Apify's Scale and Business plans the per-event prices are lower (Store discounts). Set Maximum cost per run and the Actor stops cleanly when it is reached: you never pay more than that.

Tips

  • Paste share texts as they come from the Douyin app: the link inside is found and followed.
  • Put all your links in one run rather than one run per link: it is quicker.
  • Turn translation on only when you need it: the transcript in Chinese is always included.
  • If Douyin withholds a video in a run, run it again later: it was not charged.

Use it through the API

Python

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("zaiq/douyin-transcripts-scraper").call(run_input={"videos": ["https://www.douyin.com/video/7534679152504376595"], "translateTo": "English"})
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
print(row)

JavaScript

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('zaiq/douyin-transcripts-scraper').call({"videos": ["https://www.douyin.com/video/7534679152504376595"], "translateTo": "English"});
const { items } = await client.dataset(run.defaultDatasetId).listItems();

HTTP (one call, results back)

curl -X POST 'https://api.apify.com/v2/acts/zaiq~douyin-transcripts-scraper/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>' \
-H 'Content-Type: application/json' \
-d '{"videos": ["https://www.douyin.com/video/7534679152504376595"], "translateTo": "English"}'

Integrations and schedules

  • Schedules: run it every hour, day or week from the Apify Console (Schedules) and keep a history of results.
  • Make, Zapier, n8n, Google Sheets, Slack, Airtable: connect it through Apify's integrations, or send each finished run to a webhook.
  • Datasets: results stay in the run's dataset; export them or read them by API whenever you need them.

Use it with AI agents (MCP)

Add Apify's MCP server (https://mcp.apify.com) to Claude, ChatGPT, Cursor, VS Code or any MCP client. The agent can find this Actor and run it for you: ask it for "write down what is said in these 20 Douyin videos and translate it into English". AI agents can also pay for runs directly through Apify's agentic payments.

Limits

  • Videos up to 10 minutes are written down in full (in 2-minute pieces, so long speech is not cut off); longer ones get their details and a note.
  • The transcript is written by Google's newest Gemini Flash model from the video's own sound track. Loud music and heavy background noise can drop words, and timestamps are close but not frame-exact.
  • Photo posts have no speech: they get their details only.
  • Deleted, private and region-locked videos are not shown to signed-out visitors; they are listed in SUMMARY and not charged.

FAQ

Do I need a Douyin account?

No. Everything comes from what Douyin shows a signed-out visitor.

Which languages?

Transcripts are in the language spoken (usually Mandarin Chinese). Translation into English and 18 other languages is optional.

Can I put many videos in one run?

Yes, as many as you like, in one list.

What about videos with only music?

They get a note and are not charged for a transcript.

How long can a video be?

Up to 10 minutes for a transcript.

Can I get subtitles?

Yes: keep Timestamps on and each row carries an SRT file as text.

Support

Questions, a site that changed, or a field you need? Open an issue on this Actor's Issues tab: we answer there, usually within a day.


Also found as: douyin transcript, douyin transcripts scraper, douyin video to text, 抖音 视频转文字, 抖音字幕, douyin subtitles, douyin srt, douyin translation, chinese video transcript, douyin api.