Agent skill

Douyin Transcribe

by chubbyguan in chubbyguan/chubbyskills

抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流. An agent skill from chubbyguan/chubbyskills.

MITAuto-check: notesMedia & Creative

Install Douyin Transcribe

skills CLI
$ npx skills add chubbyguan/chubbyskills --skill douyin-transcribe -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install chubbyguan/chubbyskills douyin-transcribe --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/chubbyguan/chubbyskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/douyin-transcribe .claude/skills/douyin-transcribe && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
douyin-transcribe
GitHub stars
1.2k
Token cost
~551 tokens
SKILL.md length
105 words
Files
4 (incl. scripts)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流. An agent skill from chubbyguan/chubbyskills.

  • Works in 3 steps: 从抖音下载音频 → SenseVoice-Small 转录 → 生成 Markdown
  • Tasks that involve Transcription
  • SKILL.md covers 环境要求, 使用方法, 流程(3 步) and 性能数据, plus 3 more sections
  • Runs Python scripts from its folder; calls python and pip; reaches v.douyin.com

What it does

Douyin Transcribe is an agent skill from chubbyguan/chubbyskills. 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)。

Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/download_douyin_audio.py` and `scripts/transcribe.py`).

It sits in Media & Creative, covering Transcription and Markdown. It works with Douyin. The repository describes itself as: 把中文全渠道内容(抖音 / B站 / 小红书 / 公众号 / X / 播客)采集进个人知识库的 14 个 AI Skill:图文存图、视频转文字稿、字幕优先免 GPU、RSS/YouTube 订阅调度与每日情报简报,附带知识库 MCP server。| Ingest Chinese content into your personal knowledge… The licence is MIT.

When your agent uses it

  • Tasks that involve Transcription
  • Tasks that involve Markdown

Example prompts

  • “/douyin-transcribe”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. 从抖音下载音频
  2. SenseVoice-Small 转录
  3. 生成 Markdown

What it can do on your machine

Read from SKILL.md and the folder at commit 1b759b1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • v.douyin.com

    Also links to:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Douyin Transcribe loads about 551 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 105 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~551

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:29
    # Ubuntu: sudo apt install ffmpeg

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from chubbyguan/chubbyskills at commit 1b759b1, republished under its MIT licence (© chubbyguan). 105 words, ~551 tokens.

Download SKILL.mdSave it as .claude/skills/douyin-transcribe/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
douyin-transcribe
description
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)。
metadata.category
media
metadata.triggers
["用户发送抖音分享链接或口头提到要转录抖音视频", "把这个抖音视频转成文字", "帮我转录这个抖音"]
metadata.version
1.0.0
metadata.tags
["media", "audio", "video", "transcription", "douyin"]

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
  • yt-dlp 不可用(需要 cookie),必须走 iesdouyin 路线

参考项目

⚖️ 合规声明

仅供个人学习与研究使用。请遵守目标平台的服务条款(ToS)与 robots 规则,控制请求频率,不要用于批量抓取、商用爬取或侵犯他人权益的场景。下载内容的版权归原作者所有。

© chubbyguan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in douyin-transcribe of chubbyguan/chubbyskills.

  • SKILL.md
  • requirements.txt
  • scripts/download_douyin_audio.py
  • scripts/transcribe.py

Open the folder on GitHubat commit 1b759b1

Compare with similar skills

Douyin Transcribe next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Douyin Transcribe compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Douyin Transcribe this skillchubbyguan/chubbyskills1.2k—~551Automated safety check: NotesMIT
Lingzaoatian-create/lingzao-skill2961 repos~8.8kAutomated safety check: PassMIT
Video SummaryLeoYeAI/openclaw-master-skills2.2k—~4.2kAutomated safety check: PassMIT
Video To Textdavepoon/buildwithclaude3.6k—~295Automated safety check: PassMIT
Dy NoteRimagination/dy-note172—~4.5kAutomated safety check: PassMIT
Video To Subtitle Summaryimlewc/video-to-subtitle-summary-skill218—~4.6kAutomated safety check: NotesMIT

Similar skills

  • Lingzao

    atian-create/lingzao-skill

    Use Lingzao creator-content tools for Xiaohongshu/XHS, Douyin, and WeChat official-account public content.

    296 GitHub starsUsed in 1 repo~8.8k tokens
    Media & CreativeAuto-check passed
  • Video Summary

    LeoYeAI/openclaw-master-skills

    Video summarization for Bilibili, Xiaohongshu, Douyin, and YouTube.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Video To Text

    davepoon/buildwithclaude

    视频转文字。用户发抖音分享链接(获取标题/作者/点赞等元数据),或本地视频文件(语音转写全文)时使用。抖音链接用 SSR 解析无需 Cookie。Video to text: extract metadata from Douyin share links, or transcribe speech from local video files.

    3.6k GitHub stars~295 tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Dy Note

    Rimagination/dy-note

    DyNote: systematically and efficiently extract raw Douyin/DY video data and analyze videos, comments, accounts, hashtags, and short-video scenes into evidence-graded learning notes, summaries…

    172 GitHub stars~4.5k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed
  • Video To Subtitle Summary

    imlewc/video-to-subtitle-summary-skill

    A skill your agent uses when user provides a short video platform URL or local video/audio file and wants subtitles/AI summary, or when user asks to list their own AI Douyin historical tasks.

    218 GitHub stars~4.6k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • Hotclip

    xixihhhh/hotclip

    Turn long videos & livestream VODs into viral vertical shorts, 100% locally — on-device transcription, LLM highlight detection, 9:16 reframe with karaoke captions, and a per-clip render-QA report.

    310 GitHub stars~1.1k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed

More from chubbyguan/chubbyskills

All 14 skills in this repo
  • Bilibili Transcribe

    chubbyguan/chubbyskills

    哔哩哔哩视频 → 下载 → 转录 → 存为 Markdown 的完整工作流. An agent skill from chubbyguan/chubbyskills.

    1.2k GitHub stars~578 tokensUpdated 3 days ago
    Auto-check: notes
  • Industry Intelligence Radar

    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

    1.2k GitHub stars~806 tokensUpdated 3 days ago
    Auto-check passed
  • Knowledge Base Management

    chubbyguan/chubbyskills

    管理本地 Markdown/Obsidian 知识库:素材入库、健康检查、增量索引、关键词与 semantic-lite 检索、逐字原文资料包、归档和 MCP 连接。用于搜索知识库、整理资料及为 Agent 准备可定位的引用。

    1.2k GitHub stars~3.3k tokensUpdated 3 days ago
    Auto-check passed
  • Learning Notes Automation

    chubbyguan/chubbyskills

    学习笔记自动化:视频/播客转录 → 知识点提取 → 闪卡生成 → 知识图谱更新。触发词:学习笔记、闪卡、Anki、知识提取、视频学习

    1.2k GitHub stars~898 tokensUpdated 3 days ago
    Auto-check passed
  • Podcast Transcribe

    chubbyguan/chubbyskills

    播客/小宇宙 → 下载 → 转录 → 存为 Markdown 的完整工作流. An agent skill from chubbyguan/chubbyskills.

    1.2k GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check: notes
  • Tiktok Transcribe

    chubbyguan/chubbyskills

    TikTok 视频 → 下载 → 转录 → 存为 Markdown. An agent skill from chubbyguan/chubbyskills.

    1.2k GitHub stars~536 tokensUpdated 3 days ago
    Auto-check: notes

Works with

Questions about Douyin Transcribe

What does Douyin Transcribe do?

抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流. An agent skill from chubbyguan/chubbyskills. Douyin Transcribe is an agent skill from chubbyguan/chubbyskills.

When should I use Douyin Transcribe?

Douyin Transcribe fits situations like: tasks that involve Transcription; tasks that involve Markdown.

How do I install Douyin Transcribe in Claude Code?

Run `npx skills add chubbyguan/chubbyskills --skill douyin-transcribe -a claude-code`. Or copy the skill folder (douyin-transcribe in chubbyguan/chubbyskills) into .claude/skills/douyin-transcribe in your project. Claude Code loads it when a task matches its description.

How do I install Douyin Transcribe in Codex?

Run `npx skills add chubbyguan/chubbyskills --skill douyin-transcribe -a codex`. Or copy the skill folder (douyin-transcribe in chubbyguan/chubbyskills) into .agents/skills/douyin-transcribe in your project. Codex loads it when a task matches its description.

Can I use Douyin Transcribe in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add chubbyguan/chubbyskills --skill douyin-transcribe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/douyin-transcribe, .gemini/skills/douyin-transcribe, .github/skills/douyin-transcribe and .opencode/skills/douyin-transcribe in your project.

What does Douyin Transcribe need to run?

Going by SKILL.md and its folder, Douyin Transcribe needs Python for the scripts in its folder and the command-line tools its instructions call (python and pip). Our summary lists: Python 3.

Does Douyin Transcribe access the network?

SKILL.md names 2 domains. In commands or code: v.douyin.com; the agent is likely to contact it when it follows the instructions. As links in the text: github.com. This is read from the text; nothing was executed.

Is Douyin Transcribe safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Douyin Transcribe use?

Douyin Transcribe is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Douyin Transcribe use?

About 551 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Douyin Transcribe?

Skills that share tags, products or a category with Douyin Transcribe: Lingzao (atian-create/lingzao-skill, 296 stars), Video Summary (LeoYeAI/openclaw-master-skills, 2.2k stars), Video To Text (davepoon/buildwithclaude, 3.6k stars) and Dy Note (Rimagination/dy-note, 172 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Douyin Transcribe?

chubbyguan (a GitHub user) maintains it in chubbyguan/chubbyskills, which has 1,217 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.

Source: chubbyguan/chubbyskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.