wechat-audio-toolkit vs Speak AI
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). Speak AI is an MCP server published by speakai. Marketplaces we read that list it: 2 (Official MCP Registry, Claude Code: claude-plugins-community). 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
| Marketplace |  wechat-audio-toolkit |   Speak AI |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 0.1.0 Forks (GitHub): 0 Stars (GitHub): 0 Not marked · First seen |
Listed Version: 1.19.0 Forks (GitHub): 0 Stars (GitHub): 0 Not marked · First seen |
| Official MCP Registry | Not listed | Listed Version: 1.39.0 Downloads/month (npm): 4 461 Downloads/week (npm): 819 Forks (GitHub): 0 Stars (GitHub): 0 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
| Fact | wechat-audio-toolkit | Speak AI |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 2 (better) |
| Stars (GitHub) | 0 | 0 |
| Forks (GitHub) | 0 | 0 |
| Last release (differs) | Not published | 2026-10-19 |
| Where it runs (differs) | Installs as a plugin bundle | Remote server or your machine |
| Transport (differs) | Not stated | Streamable HTTP |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 2, secrets among them: 1 |
| Parts of the bundle (differs) | 2 | 6 |
| Licence | MIT | MIT |
| Repository (differs) | github.com/guoxiaowen/wechat-audio-toolkit | github.com/speakai/speakai-mcp |
| Changes in the last 7 days (differs) | 0 | 7 |
| First seen (differs) | 2026-10-12 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 5 days ago, requires a key |
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
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.
Speak AI
Search recordings, summarize meetings, create clips, and automate workflows from your AI assistant.
How to run each
wechat-audio-toolkit As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install wechat-audio-toolkit@claude-communitySpeak AI As a remote MCP server
claude mcp add --transport http speak-ai https://api.speakai.co/v1/mcpRequires: SPEAK_API_KEY (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only Speak AI has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of wechat-audio-toolkit publish no settings it asks for, so we do not compare settings.
What it can do: wechat-audio-toolkit · What it can do: Speak AI · 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.