Ext Ops Panel
Open dashboard
Comparison

wechat-audio-toolkit vs FunASR

wechat-audio-toolkit is a plugin bundle for AI coding tools published by guoxiaowen. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). FunASR is an MCP server published by modelscope. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-19. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplacewechat-audio-toolkitFunASR
Claude Code: claude-plugins-community Listed
Version: 0.1.0
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.1.2
Forks (GitHub): 2 085
Stars (GitHub): 20 740
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

wechat-audio-toolkit vs FunASR
Factwechat-audio-toolkitFunASR
Marketplaces that list it11
Stars (GitHub) (differs)0 (worse)20 740 (better)
Forks (GitHub) (differs)0 (worse)2 085 (better)
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleOn your machine (ghcr.io/modelscope/funasr-mcp:0.1.2)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Parts of the bundle (differs)2Not a bundle
Licence (differs)MITNot stated
Repository (differs)github.com/guoxiaowen/wechat-audio-toolkitgithub.com/modelscope/funasr
Changes in the last 7 days00
First seen (differs)2026-10-122026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

wechat-audio-toolkit

In its own words, on Claude Code: claude-plugins-community:

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.

FunASR

In its own words, on Official MCP Registry:

Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

How to run each

wechat-audio-toolkit As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install wechat-audio-toolkit@claude-community

FunASR As a local MCP server: Docker image

Claude Code
claude mcp add --transport stdio funasr-mcp -- docker run -i --rm --mount "type=bind,src=<YOUR_AUDIO_DIRECTORY>,dst=/audio,readonly" --mount type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope ghcr.io/modelscope/funasr-mcp:0.1.2

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

Neither one's marketplaces publish the settings it asks for.

What it can do: wechat-audio-toolkit · What it can do: FunASR · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built