Plugin

wechat-audio-toolkit

中文音频 → 公众号 Markdown 文章 / 文字稿。基于阿里云 DashScope paraformer-v2 实现语音识别 + 说话人分离，最长支持 12 小时音频。包含两个 skill：audio-to-wechat-md 自动出 6000-10000 字成品文章 + 5 个标题选项；audio-to-transcript 出原样保留的可读文字稿。适合公众号创作者整理直播回放、访谈、播客等长音频内容。 Chinese audio → WeChat-formatted Markdown article or readable transcript. Backed by Aliyun DashScope paraformer-v2 (ASR with diarization). Supports up to 12-hour audio files. Two skills: audio-to-wechat-md (full WeChat article + 5 title options) and audio-to-transcript (minimally-edited readable transcript). Designed for Chinese content creators handling livestream replays, interviews, podcasts.

• Published source
• Repository

Analysed

11 October 2026

Last observed

11 October 2026

What the code does

• Runs shell commands Code that starts system commands on the machine it runs on.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.