# Douyin Transcripts Scraper: Video to Text, SRT & English (`zaiq/douyin-transcripts-scraper`) Actor 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. - **URL**: https://apify.com/zaiq/douyin-transcripts-scraper.md - **Developed by:** [Zaiq](https://apify.com/zaiq) (community) - **Categories:** Social media, Videos, AI - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $1.20 / 1,000 videos This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have. Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event ## What's an Apify Actor? An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md. ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run. For examples already wired to this Actor's own input schema, see the [API](#api) section below. Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`). # README ## 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 | Field | What it holds | |---|---| | Transcript | `transcript` (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` | | Video | `awemeId`, `text` (caption), `createdAt`, `durationSeconds`, `likes`, `comments`, `shares`, `saves`, `hashtags`, `series`, `cover`, `videoUrl`, `url` | | Author and music | `author` (name, Douyin ID, bio, posts, link), `music` (title, author) | | SUMMARY | what 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 | Field | Example | Notes | |---|---|---| | Video links | `https://www.douyin.com/video/` | Links, share links, share texts or ids; many per run | | Transcripts | on | Off: only the videos' details | | Timestamps and subtitles | on | Segments and an SRT file; no extra charge | | Translate transcripts to | English | Or 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): ```json { "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: | Job | Cost | |---|---| | 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** ```python from apify_client import ApifyClient client = ApifyClient("") 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** ```js import { ApifyClient } from 'apify-client'; const client = new ApifyClient({ 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)** ```bash curl -X POST 'https://api.apify.com/v2/acts/zaiq~douyin-transcripts-scraper/run-sync-get-dataset-items?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. ### Related Actors from Zaiq - [douyin-scraper](https://apify.com/zaiq/douyin-scraper): Douyin hot search (热榜), videos and creator profiles - [tiktok-transcript-scraper](https://apify.com/zaiq/tiktok-transcript-scraper): what is said in TikTok videos - [instagram-transcript-scraper](https://apify.com/zaiq/instagram-transcript-scraper): what is said in Instagram reels - [bilibili-scraper](https://apify.com/zaiq/bilibili-scraper): Bilibili videos, comments and danmaku ### 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. # Actor input Schema ## `videos` (type: `array`): Douyin video links (douyin.com/video/..., v.douyin.com/... share links, or a share text that contains one) or video ids, one per line. Many per run. ## `transcripts` (type: `boolean`): Write down what is said in each video up to 10 minutes long ($0.005 per started minute; silent and failed ones are free). Off: only the videos' details ($0.0015 each). ## `timestamps` (type: `boolean`): Split each transcript into timed segments (start and end in seconds) and add an SRT subtitle file. No extra charge. ## `translateTo` (type: `string`): Also give each transcript in this language (skipped when it is already in it). No extra charge from this Actor; the AI model's own cost is billed by Apify, a fraction of a cent a transcript. ## Actor input object example ```json { "videos": [ "https://www.douyin.com/video/7534679152504376595" ], "transcripts": true, "timestamps": true, "translateTo": "English" } ``` # Actor output Schema ## `results` (type: `string`): Dataset: the results. ## `summary` (type: `string`): What each input returned, and notes. # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "videos": [ "https://www.douyin.com/video/7534679152504376595" ], "translateTo": "English" }; // Run the Actor and wait for it to finish const run = await client.actor("zaiq/douyin-transcripts-scraper").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "videos": ["https://www.douyin.com/video/7534679152504376595"], "translateTo": "English", } # Run the Actor and wait for it to finish run = client.actor("zaiq/douyin-transcripts-scraper").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}") for item in client.dataset(run.default_dataset_id).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "videos": [ "https://www.douyin.com/video/7534679152504376595" ], "translateTo": "English" }' | apify call zaiq/douyin-transcripts-scraper --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,zaiq/douyin-transcripts-scraper" } } } ``` The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer ` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations). ## OpenAPI specification Download the OpenAPI definition: https://api.apify.com/v2/actors/NroY8sgu1bzLWoAjY/builds/7G75YvtOm19j9GC0D/openapi.json