# Kwai Video Scraper & Transcript (`zait_dioses/kwai-video-transcript-scraper`) Actor

Scrape public Kwai videos and profiles (views, likes, comments, author, hashtags) and get the spoken transcript of each video with Whisper — Spanish, Portuguese and 90+ languages.

- **URL**: https://apify.com/zait_dioses/kwai-video-transcript-scraper.md
- **Developed by:** [Zait Dioses](https://apify.com/zait_dioses) (community)
- **Categories:** Videos, Social media, AI
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $2.00 / 1,000 video scrapeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

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

### What does Kwai Video Scraper & Transcript do?

**Kwai Video Scraper & Transcript** extracts public data from [Kwai](https://www.kwai.com) videos and profiles, and turns what is **said in each video into text**. Paste a video link, a profile link or just a **hashtag**, and you get views, likes, comments, shares, hashtags, author stats and the full spoken transcript, with timestamps if you want them.

Kwai is one of the biggest short-video apps in **Brazil and Latin America**, and until now there was no way to get its transcripts. Transcription runs on Whisper (large-v3-turbo) and works in **Portuguese, Spanish, English and 90+ other languages**, detected automatically.

No login, no cookies, no Kwai account needed.

### Why scrape Kwai transcripts?

- 🎬 **Content research**: see what the top Brazilian and Latin American creators actually say, not only their captions.
- 🧠 **AI & LLM pipelines**: feed clean transcripts into ChatGPT, Claude or your RAG system to summarize, classify or repurpose videos.
- 📈 **Marketing & trends**: find the hooks, products and phrases that get views in your niche.
- 🔎 **Brand monitoring**: know when a product or brand is mentioned out loud, even if it's not in the caption or hashtags.
- 📝 **Subtitles & repurposing**: turn videos into blog posts, threads or subtitles (timestamps included).

### How to use it

1. Click **Try for free**.
2. Paste one or more Kwai links in **Kwai URLs**: videos (`https://www.kwai.com/@user/video/123…`) or profiles (`https://www.kwai.com/@user`). Share links work too.
   Or type **hashtags** (without the #), like `receitas`, `humor` or `futebol`, to collect the videos of a topic.
3. Choose whether to transcribe, the spoken language (or auto-detect) and whether you want timestamps.
4. Click **Start**, then download your data as JSON, CSV, Excel or HTML, or get it through the API.

### How much does it cost?

You pay only for what you get (pay-per-event):

- a small fee for each **video scraped**;
- a fee per **minute of audio transcribed**.

Money-saving defaults:

- **Videos without speech are not transcribed.** Kwai flags music-only videos, so we skip those automatically and you don't pay to transcribe them. Their data is still returned.
- **There's a cap per video** ("Max minutes to transcribe per video"), so one long video can't blow your budget.
- You can switch transcription off and use it as a plain, cheap Kwai scraper.

### Input

| Field | Description |
|---|---|
| **Kwai URLs** | Video or profile links. |
| **Hashtags** | Topics to scrape, without the #. |
| **Max videos per hashtag** | Default 50, up to 1,000. |
| **Max videos per profile** | Latest videos to take from each profile. Default 20, up to 1,000. |
| **Transcribe the audio** | On by default. |
| **Spoken language** | Auto-detect, or force Spanish, Portuguese, English, Indonesian or Arabic. |
| **Skip videos without speech** | On by default; saves money on music-only videos. |
| **Include timestamps** | Adds the transcript split into segments with start and end times. |
| **Max minutes to transcribe per video** | Default 10. |

### Output

Each video is one item. Example (shortened):

```json
{
  "videoId": "5236992052920543570",
  "url": "https://www.kwai.com/@cocinaoriental/video/5236992052920543570",
  "caption": "ri demais #video #assista #explorar",
  "hashtags": ["video", "assista", "explorar"],
  "createdAt": "2026-11-13T16:29:26.632000+00:00",
  "durationSeconds": 168.8,
  "viewCount": 610,
  "likeCount": 18,
  "commentCount": 0,
  "shareCount": 8,
  "isAiGenerated": false,
  "speechProbability": 0.9969,
  "author": {
    "kwaiId": "cocinaoriental",
    "name": "Cocina Oriental",
    "followers": 1005,
    "totalVideos": 254,
    "profileUrl": "https://www.kwai.com/@cocinaoriental"
  },
  "coverUrl": "https://…webp",
  "videoUrl": "https://…mp4",
  "transcript": "Surpreenda sua família com essa deliciosa receita de frango com batatas…",
  "transcriptLanguage": "pt",
  "transcriptSegments": [{ "start": 0.0, "end": 3.1, "text": "Surpreenda sua família…" }],
  "transcriptStatus": "ok"
}
```

`inputUrl` tells you where each video came from (the link or `#hashtag` you entered). `transcriptStatus` tells you what happened with each video: `ok`, `skipped_no_speech`, `skipped_too_long`, `disabled` or `error: …`. Profile fields (`followers`, `totalVideos`, `totalLikes`) are filled when you scrape a profile link.

### Tips

- Want only the data and no transcript? Turn off **Transcribe the audio**: it's the cheapest way to monitor Kwai profiles.
- Forcing the language (instead of auto-detect) slightly improves accuracy on short or noisy videos.
- Run it on a schedule to track a creator's new videos every day.

### FAQ

**Is it legal to scrape Kwai?** This Actor only reads data that is publicly visible on kwai.com without logging in. It does not collect private data. You are responsible for how you use the results; if they include personal data, make sure you have a legitimate reason under laws such as GDPR or Brazil's LGPD.

**How many videos can I get?** Up to 1,000 per profile and up to 1,000 per hashtag in a single run.

**Can I get the comments?** Not yet: Kwai only shows comments to logged-in users. The comment count is included for every video.

**Something broke or you need a feature?** Open an issue in the **Issues** tab and I'll get back to you quickly.

# Actor input Schema

## `startUrls` (type: `array`):

Links to Kwai videos (https://www.kwai.com/@user/video/123…) or profiles (https://www.kwai.com/@user). Share links are followed automatically.

## `hashtags` (type: `array`):

Hashtags to scrape, without the # (e.g. receitas, humor, futebol). Returns the videos Kwai shows for each one.

## `maxVideosPerHashtag` (type: `integer`):

How many videos to take from each hashtag.

## `maxVideosPerProfile` (type: `integer`):

How many of the latest videos to take from each profile.

## `transcribe` (type: `boolean`):

Turn speech into text with Whisper (large-v3-turbo). Works in Spanish, Portuguese, English and 90+ other languages.

## `language` (type: `string`):

Leave on auto-detect, or force a language for better accuracy.

## `skipVideosWithoutSpeech` (type: `boolean`):

Kwai flags videos that are only music. Skipping them saves you the transcription cost; their data is still returned.

## `includeSegments` (type: `boolean`):

Add the transcript split into segments with start and end times (for subtitles or clips).

## `maxTranscriptMinutesPerVideo` (type: `integer`):

Longer videos are returned without a transcript, so one long video can't blow your budget.

## `proxyConfiguration` (type: `object`):

Optional. Use it only if Kwai starts blocking requests.

## Actor input object example

```json
{
  "startUrls": [
    {
      "url": "https://www.kwai.com/@cocinaoriental"
    }
  ],
  "hashtags": [
    "receitas"
  ],
  "maxVideosPerHashtag": 50,
  "maxVideosPerProfile": 20,
  "transcribe": true,
  "language": "auto",
  "skipVideosWithoutSpeech": true,
  "includeSegments": false,
  "maxTranscriptMinutesPerVideo": 10,
  "proxyConfiguration": {
    "useApifyProxy": false
  }
}
```

# Actor output Schema

## `results` (type: `string`):

No description

# 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 '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "startUrls": [
        {
            "url": "https://www.kwai.com/@cocinaoriental"
        }
    ],
    "hashtags": [
        "receitas"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("zait_dioses/kwai-video-transcript-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 '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "startUrls": [{ "url": "https://www.kwai.com/@cocinaoriental" }],
    "hashtags": ["receitas"],
}

# Run the Actor and wait for it to finish
run = client.actor("zait_dioses/kwai-video-transcript-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 '{
  "startUrls": [
    {
      "url": "https://www.kwai.com/@cocinaoriental"
    }
  ],
  "hashtags": [
    "receitas"
  ]
}' |
apify call zait_dioses/kwai-video-transcript-scraper --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,zait_dioses/kwai-video-transcript-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 <APIFY_API_TOKEN>` 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/hqvTFNyLXv6ERXzFz/builds/JY74LgcaL6H1qnlu8/openapi.json