Install Weibo Transcribe
Pick your agent. Every command is ready to paste.
npx skills add chubbyguan/chubbyskills --skill weibo-transcribeThe open skills CLI detects your agents (Claude Code, Cursor, Codex and 70+ more) and installs to the right folder. Add -g to install globally.
01
Install it
Run the command above, or upload the folder in Claude.
02
Ask naturally
Describe the task. Your agent loads weibo-transcribe when the request matches its description.
03
Name it if needed
If it does not trigger, say “use the weibo-transcribe skill”. In Codex, type $weibo-transcribe.
微博视频转录 Skill
将微博视频下载音频,用 SenseVoice-Small 转录为文字,存为带 frontmatter 的 Markdown 文件。
环境要求
# 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 yt-dlp
# Ubuntu: sudo apt install ffmpeg && pip install yt-dlp
使用方法
# 桌面端链接
python scripts/transcribe.py "https://weibo.com/xxxxx"
# 移动端链接(更稳定)
python scripts/transcribe.py "https://m.weibo.cn/xxxxx"
# 指定输出目录
python scripts/transcribe.py "https://m.weibo.cn/xxxxx" -o ./output
流程
Step 1: yt-dlp 下载音频
微博对桌面端 UA 拦截较严,脚本自动使用移动端 UA + Referer 伪装。优先用 m.weibo.cn 链接,成功率更高。
yt-dlp --extract-audio --audio-format mp3 --audio-quality 128K \
--user-agent "Mozilla/5.0 (iPhone; CPU iPhone OS 16_0 like Mac OS X) ..." \
--referer "https://m.weibo.cn/" \
"https://m.weibo.cn/status/example"
Step 2: SenseVoice-Small 转录
from funasr import AutoModel
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
脚本自动创建带 frontmatter 的 Markdown 文件,包含来源链接、作者、语言和转录文本。下载失败会自动重试。
已知限制
- 链接形态:桌面端
weibo.com链接常被反爬拦截,优先使用m.weibo.cn移动端链接 - 反爬:微博对非移动端 UA 和缺失 Referer 的请求拦截较严;脚本已内置移动端 UA,但频繁请求仍可能触发限流
- 登录态:私密博文、仅粉丝可见内容需要登录,当前脚本不携带登录态
- 语言:微博以中文为主,脚本默认
language=zh;英文内容建议改用 youtube-transcribe - 模型大小:SenseVoice-Small 首次下载约 893MB
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。
Tips for Weibo Transcribe
- • Start a fresh session after installing so your agent picks up the new skill.
- • This skill ships scripts. Read them before the first run, and run it in a project without secrets first.
- • It is part of a pack with 14 skills. Install only the ones you need with --skill to keep triggers precise.
- • If two skills overlap, mention the one you want by name.
Questions about Weibo Transcribe
What does the Weibo Transcribe skill do?
微博视频 → 下载 → 转录 → 存为 Markdown。 支持 weibo.com 和 m.weibo.cn 链接,无需登录。
How do I install Weibo Transcribe?
Run "npx skills add chubbyguan/chubbyskills --skill weibo-transcribe" in your project. The skills CLI installs it for Claude Code, Cursor, Codex and 70+ other agents. In Claude on the web, upload the skill folder as a ZIP under Customize > Skills.
Does Weibo Transcribe work in Cursor and Codex?
Yes. Weibo Transcribe uses the open SKILL.md format, so it works in Claude Code, Claude, Cursor, OpenAI Codex, Gemini CLI, GitHub Copilot and other agents that support agent skills.
Is Weibo Transcribe free?
Weibo Transcribe is open source on GitHub under the MIT license. It is free to install; check the license before commercial use.
Who made Weibo Transcribe?
Weibo Transcribe is published by chubbyguan in the chubbyguan/chubbyskills repository, together with 13 other skills.

