给Claude、Cursor、VS Code、Windsurf或任何MCP客户端 ， 和 。不上传，不带API密钥，不使用账户。
概览
给Claude、Cursor、VS Code、Windsurf或任何MCP客户端 ， 和 。不上传，不带API密钥，不使用账户。 Yap MCP 运行与 Yap 语音输入应用相同的语音引擎：NVIDIA Parakeet TDT v3，通过 sherpa-onnx 运行在你的 CPU 上。音频从不离开你的机器;唯一的网络请求是一次性通过校验和验证的语音模型下载，来自 Hugging Face。 问你的助理一些问题，比如“带时间戳转录~/下载/interview.m4a”、“在桌面上总结语音备忘录”，或者“我这周对预算有什么决定？”。 需要Node.js 20及以上（search_dictations需22.13+）。macOS（Apple Silicon和Intel）、Windows x64和Linux x64/arm64。 下载 yap.mcpb 并打开（macOS 和 Windows）。或者添加内容claude_desktop_config.json： ： /plugin marketplace 添加 founden-bot/yap-mcp，然后 /plugin 安装 yap@yap。插件从自己的文件夹（node ${CLAUDE_PLUGIN_ROOT}/src/index）运行服务器。
概述（AI 翻译）
让Claude、Cursor、VS Code、Windsurf或任何MCP客户端都能在自己的电脑上转录音频文件，并且用Yap应用搜索你口述的内容。没有上传，没有API密钥，没有账户。
Yap MCP 运行与 Yap 语音输入应用相同的语音引擎：NVIDIA Parakeet TDT v3，通过 sherpa-onnx 运行在你的 CPU 上。音频从不离开你的机器;唯一的网络请求是一次性通过校验和验证的语音模型下载，来自 Hugging Face。
工具
| 工具 | 它的作用 |
|---|---|
transcribe_audio |
转录任意长度的本地音频或视频文件：WAV、MP3、M4A/AAC、MP4、FLAC、OGG、Opus、WebM、AIFF、CAF 等。自动在25种欧洲语言中检测该语言。每篇文章可选起始时间戳和Yap的清理（大写、标点、“um”去除）。 |
search_dictations |
搜索Yap应用在这台电脑（Mac和Windows）上的语音输入历史，优先选最新。只读。 |
prepare_speech_model |
在首次转录前下载并验证语音模型，或报告其状态。 |
问你的助理一些问题，比如“转录~/下载/采访。
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
Yap MCP: private, on-device speech to text for AI assistants
Give Claude, Cursor, VS Code, Windsurf or any MCP client the ability to transcribe audio files on your own computer, and to search what you dictated with the Yap app. No upload, no API key, no account.
Yap MCP runs the same speech engine as the Yap dictation app: NVIDIA Parakeet TDT v3 through sherpa-onnx, on your CPU. Audio never leaves your machine; the only network request is a one-time, checksum-verified download of the speech model (about 670 MB) from Hugging Face.
Tools
| Tool | What it does |
|---|---|
transcribe_audio |
Transcribes a local audio or video file of any length: WAV, MP3, M4A/AAC, MP4, FLAC, OGG, Opus, WebM, AIFF, CAF and more. Detects the language automatically among 25 European languages. Optional start-time stamps per passage and Yap’s cleanup (capitalization, punctuation, “um” removed). |
search_dictations |
Searches the dictation history the Yap app keeps on this computer (Mac and Windows), newest first. Read-only. |
prepare_speech_model |
Downloads and verifies the speech model ahead of the first transcription, or reports its status. |
Ask your assistant things like “transcribe ~/Downloads/interview.m4a with timestamps”, “summarize the voice memo on my desktop”, or “what did I dictate about the budget this week?”.
Install
Requires Node.js 20 or newer (22.13+ for search_dictations). macOS (Apple Silicon and Intel), Windows x64 and Linux x64/arm64.
Claude Desktop, one click: download yap.mcpb and open it (macOS and Windows). Or add to claude_desktop_config.json:
{
"mcpServers": {
"yap": { "command": "npx", "args": ["-y", "github:founden-bot/yap-mcp"] }
}
}
Claude Code:
claude mcp add yap -- npx -y github:founden-bot/yap-mcp
Claude Code plugin: /plugin marketplace add founden-bot/yap-mcp, then /plugin install yap@yap. The plugin runs the server from its own folder (node ${CLAUDE_PLUGIN_ROOT}/src/index.js) with the dependencies pinned in package-lock.json, and adds the transcribe-recordings skill.
Gemini CLI: gemini extensions install https://github.com/founden-bot/yap-mcp.
Cursor, Windsurf, VS Code, Cline, Zed and other clients: add a stdio server with command npx and arguments -y github:founden-bot/yap-mcp.
The first transcription downloads the model once (a few minutes on a typical connection) and answers with the progress while it does; after that, everything runs offline. Transcription runs about ten times faster than real time on a modern laptop, so an hour of audio takes about six minutes.
In the terminal
The same engine as a command: npx -y -p github:founden-bot/yap-mcp yap-transcribe memo.m4a prints the transcript (add --timestamps for start times, several files at once are fine).
Languages
安装
npx -y github:founden-bot/yap-mcp配置
{
"mcpServers": {
"yap": { "command": "npx", "args": ["-y", "github:founden-bot/yap-mcp"] }
}
}