Zhihu Transcribe

by chubbyguan

Zhihu Transcribe is an AI Engineering skill for Claude Code, published by chubbyguan in chubbyskills.

637 stars90 forkson chubbyguan/chubbyskillsAdded 2026/08/24+2% in starsRepository updated 2026/08/19

View source on GitHub Download repo ZIP

agent-skillsai-agentschineseclaude-codeknowledge-basemcpobsidiansecond-braintranscriptionxiaohongshu

Install in seconds

Install Zhihu Transcribe

Copy Zhihu Transcribe into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/chubbyguan/chubbyskills/tree/main/zhihu-transcribe ~/.claude/skills/zhihu-transcribe

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/chubbyguan/chubbyskills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: zhihu-transcribe/SKILL.md in chubbyguan/chubbyskills
Installs to: ~/.claude/skills/zhihu-transcribe
Collection: One of 14 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Zhihu Transcribe does

Zhihu Transcribe downloads Zhihu video audio, transcribes it with SenseVoice-Small, and saves the result as a Markdown file. Use it when you want a text transcript from a Zhihu video link without logging in.

Zhihu Transcribe is cataloged under AI Engineering on DirSkills. Zhihu Transcribe comes from a repository tagged agent-skills, ai-agents, chinese, claude-code and knowledge-base.

Documentation

README

From the original repository

知乎视频转录 Skill

将知乎视频下载音频，用 SenseVoice-Small 转录为文字，存为 Markdown 文件。

环境要求

pip install funasr modelscope torch torchaudio
brew install ffmpeg yt-dlp  # macOS

使用方法

python scripts/transcribe.py "https://www.zhihu.com/xxxxx"
python scripts/transcribe.py "https://www.zhihu.com/video/xxxxx"

流程

yt-dlp 下载知乎视频音频
SenseVoice-Small 转录
生成带 frontmatter 的 Markdown

已知限制

部分知乎视频可能需要登录才能访问
SenseVoice-Small 主要针对中文优化

致谢

yt-dlp/yt-dlp — 视频下载工具
FunAudioLLM/SenseVoice — 语音识别模型

⚖️ 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。

Frequently asked about Zhihu Transcribe

What else does chubbyguan publish alongside Zhihu Transcribe?
Zhihu Transcribe is one of 14 skills that DirSkills catalogs from chubbyguan/chubbyskills, the repository it ships in. Its siblings there include Bilibili Transcribe, Content Enrich and Douyin Transcription. Each one is a separate skill with its own page in this directory, installs the same way Zhihu Transcribe does, and is maintained by chubbyguan in that same repository. The rest of the collection is listed on the chubbyguan/chubbyskills page.
How does Zhihu Transcribe compare to other AI Engineering skills?
Zhihu Transcribe ranks #1873 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Zhihu Transcribe against them. Open each page to compare what they document and how they install.