Douyin Transcribe

抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持短链接和完整链接;优先无 cookie 直采,被风控时回退 yt-dlp + 浏览器 cookie(无需登录)。

1,337 stars 155 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add chubbyguan/chubbyskills --skill douyin-transcribe
Manual install
git clone --depth 1 https://github.com/chubbyguan/chubbyskills.git /tmp/chubbyskills
mkdir -p ~/.claude/skills
cp -r /tmp/chubbyskills/douyin-transcribe ~/.claude/skills/douyin-transcribe

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 抖音视频转录 Skill

将抖音视频下载音频,用 SenseVoice-Small 转录为文字,存为 Markdown 文件。

## 环境要求

```bash
# Python 3.9+
python -m venv .venv
source .venv/bin/activate

# 依赖
pip install funasr modelscope torch torchaudio

# 系统依赖
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg
```

## 使用方法

```bash
python scripts/transcribe.py "https://v.douyin.com/xxxxx"
```

## 流程(3 步)

### Step 1: 从抖音下载音频

使用 `iesdouyin.com/share/video/<id>` + 移动端 UA 获取 `window._ROUTER_DATA`,提取 CDN 下载链接。

**关键点:**
- ✅ `iesdouyin.com/share/video/` 而非 `douyin.com/video/`
- ✅ 移动端 UA 必须用 iPhone
- ✅ `playwm` → `play` 去水印
- ⚠️ 首选无 cookie 直采;若分享页返回蜘蛛壳(风控),自动回退 yt-dlp + `YTDLP_COOKIES_FROM_BROWSER`(浏览器打开过 douyin.com 即可,无需登录)

### Step 2: SenseVoice-Small 转录

```python
from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess

model = AutoModel(
    model="iic/SenseVoiceSmall",
    trust_remote_code=True,
    vad_model="fsmn-vad",
    vad_kwargs={"max_single_segment_time": 30000},
    device="cpu",
)

result = model.generate(input=audio_path, language="zh", use_itn=True, batch_size_s=60)
```

### Step 3: 生成 Markdown

自动创建带 frontmatter 的 Markdown 文件。

## 性能数据

| 视频时长 | 模型加载 | 转录耗时 | 总耗时 |
|------|------|------|------|
| 10 min | ~30s | ~25s | ~1 min |
| 30 min | ~30s | ~75s | ~2 min |
| 1h 22min | ~40s | ~180s | ~4 min |

## 已知限制

- SenseVoice-Small 模型首次下载约 893MB(从 ModelScope,国内快)
- CPU 推理质量略低于 GPU,但中文仍优于 Whisper-small
- VAD 自动切分可能把长停顿处切成两段
- 不支持说话人分离
Read the full skill on GitHub

Details

Skill name
douyin-transcribe
Path
douyin-transcribe/SKILL.md
License
MIT
Repo updated
14 October 2026

FAQ

What does the Douyin Transcribe skill do?

抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持短链接和完整链接;优先无 cookie 直采,被风控时回退 yt-dlp + 浏览器 cookie(无需登录)。

How do I install the Douyin Transcribe skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add chubbyguan/chubbyskills --skill douyin-transcribe. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Douyin Transcribe popular?

It lives in chubbyguan/chubbyskills, which has 1,337 GitHub stars and 155 forks, and is included in 1 curated skill list.

Related skills

Bilibili Transcribe

1.3k

chubbyguan/chubbyskills

哔哩哔哩视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持 BV 号和完整链接,无需登录。

Images, Video & AudioIn 1 list155

Content Enrich

1.3k

chubbyguan/chubbyskills

内容加工:给任意采集产物(转录稿 / 文章 / 笔记)自动补「摘要 + 要点 + 标签 + 价值判断」, 写进 frontmatter 并在正文顶部插入摘要块。是「加工层」通用能力,惠及仓库所有采集 skill。

Writing & ContentIn 1 list155

Industry Intelligence Radar

1.3k

chubbyguan/chubbyskills

行业情报雷达:多源扫描(X/即刻/V2EX/HN) → 关键词过滤 → 趋势检测 → 每日情报简报。触发词:行业情报、竞品监控、热点扫描、情报雷达

OtherIn 1 list155

Podcast Transcribe

1.3k

chubbyguan/chubbyskills

播客/小宇宙 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持 RSS 批量下载、单集链接转录。

Images, Video & AudioIn 1 list155

Tiktok Transcribe

1.3k

chubbyguan/chubbyskills

TikTok 视频 → 下载 → 转录 → 存为 Markdown。 支持 vm.tiktok.com / vt.tiktok.com 短链和完整链接,无需登录。

Images, Video & AudioIn 1 list155

Sw Scene Craft

2.1k

jtydhr88/screenwriting-skills

Scene and sequence craft (场景/段落/细节/道具/悬念/情趣) — merged from Robert McKee's scene design and five-step scene analysis (value turn, beats, text/subtext, turning points, pacing, image systems), McKee's Dialogue scene types (balanced, comic, asymmetric, indirect, reflexive, minimal), Syd Field's sequence and scene elements, Neill Hicks (less is more, enter late leave early, energy), Richard Walter (action over talk, small gestures, avoid phones/cars/restaurants, list twelve alternative locations), Wendy Henson (action paragraphs, transitions, story-doing), Julian Hoxter (scene beats, objectives and

Images, Video & Audio220

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.