Whispernotes

io.github.mazzzystar由 GitHub 账号 mazzzystar 发布v0.2.0更新于 Oct 24, 2026

Search, read, and create speech-to-text transcripts on-device with the Whisper Notes Mac app.

概览

AI 生成的概览

让助手搜索、读取并创建 Whisper Notes Mac 应用中的本地语音转文字记录。

可以做什么
该服务器提供工具,用于列出最近的转录记录、在转录历史中进行全文搜索,以及获取单条转录的纯文本、带时间戳或带说话人标注的版本。它还能转录本地音频或视频文件并将结果保存到历史记录,并列出已安装的转录模型。较长的录音会分页返回,便于分段读取。
适用场景
适合在 Mac 上用 Whisper Notes 保存会议、语音备忘或访谈录音,并希望助手搜索、总结或提取待办事项的场景。也适合希望转录内容留在本机、注重隐私的工作流程。
运行要求
需要 macOS 14 或更高版本的 Apple 芯片 Mac,以及 Whisper Notes for Mac 1.5.5 或更高版本的直接下载(DMG)版本;Mac App Store 版本不含 Local API。MCP 服务器内置于应用中,无需 npm 或 pip 安装。需在应用设置中开启 Local CLI & MCP、安装 CLI,并让 MCP 客户端通过 stdio 调用 whispernotes 命令并传入 mcp 参数。
安装前请注意
该服务器会创建新的转录并写入本地历史记录,也会读取转录文本和你指定的本地音频或视频文件。它通过权限为 0600 的本地 Unix 套接字运行,未开启前不提供任何服务,也没有网络端点。MCP 客户端会在每次工具调用前请求批准。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Whispernotes,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Whisper Notes MCP Server & CLI

MCP server and command-line access to Whisper Notes — on-device speech-to-text for Mac and iPhone. Claude and any MCP client can search your transcript history, read transcripts (plain, timestamped, or speaker-labeled), and transcribe audio or video files.

100% on-device. The server speaks over a local Unix socket (0600 permissions) — no open ports, no network interface, no cloud. Your audio and transcripts never leave your Mac.

The MCP server is built into the Whisper Notes Mac app — there is nothing to npx or pip install. This repository is its documentation and registry home. Canonical docs live at whispernotes.app/cli-mcp (agent-readable markdown: whispernotes.app/cli-mcp.md).

Set up

  1. Download Whisper Notes for Mac 1.5.5 or later — Direct Download (DMG) version (the Mac App Store build does not include the Local API). macOS 14+, Apple Silicon.
  2. Open the app → Settings → Integrations → toggle on Local CLI & MCP.
  3. Click Install CLI in the same section — this puts whispernotes (and the wn shorthand, when that name is free) in your terminal.

Connect Claude or any MCP client

Claude Code — one line:

bash
claude mcp add whispernotes -- whispernotes mcp

Claude Desktop — add this to ~/Library/Application Support/Claude/claude_desktop_config.json, then restart Claude Desktop:

json
{  "mcpServers": {    "whispernotes": {      "command": "/usr/local/bin/whispernotes",      "args": ["mcp"]    }  }}

Use the full path from which whispernotes — GUI apps don't read your shell's PATH. Any other local MCP client (Cursor, etc.) works the same way: command whispernotes, args ["mcp"]. Transport is stdio; there is no HTTP endpoint.

Then just ask:

  • "Read my last five transcripts and tell me what I should follow up on."
  • "Find the meeting where we discussed the invoice, and draft a reply email."
  • "Transcribe ~/Desktop/podcast.mp3 and pull out every action item."

MCP tools

ToolParametersReturns
list_transcriptslimit (default 20) · sourceRecent transcripts with ids, dates, titles
search_transcriptsquery (required) · limitFull-text matches with snippets
get_transcriptid (required) · timestamps · speakers · max_chars · offsetOne transcript's text
get_latest_transcripttimestamps · speakersYour most recent transcript
transcribe_filepath (required)Transcribes an audio or video file, saves it to history
list_models—Installed models and which one is active

Long recordings are paged: when a transcript exceeds max_chars, the response ends with an explicit truncation marker telling the agent which offset to continue from — hour-long meetings never overflow a context window.

CLI

The same binary is a full command-line tool:

bash
$ whispernotes statusWhisperNotes 1.5.5 (340) · SenseVoice Small · ready · 3081 notes
$ whispernotes list --limit 39f3c21a8  2026-08-01 09:14  0:42   meeting   Weekly sync — pricing reviewb2d84e07  2026-07-31 18:03  12:26  recorded  Idea dump on the walk home5a1f9c33  2026-07-30 10:52  47:10  imported  interview-with-anna.m4a
$ whispernotes show latest | ollama run llama3 "Summarize the key points:"
$ whispernotes export --format md --audio --output-dir ~/Transcripts✓ exported 312/312 transcript(s), 312 audio file(s) → /Users/you/Transcripts
CommandOptionsWhat it does
status—App version, active model, readiness, note count
list--limit N · --source T · --jsonRecent transcripts, newest first
search <query>--limit N · --jsonFull-text search across your history, with snippets
show [id or latest]--timestamps · --speakers · --max-chars N · --offset N · --jsonPrint one transcript (defaults to latest)
transcribe <file>--jsonTranscribe an audio or video file, save it to history
export--format txt or md · --output-dir DIR · --source T · --limit N · --audio · --speakersBatch-export transcripts, optionally copying the audio alongside
modelslist · select <id>List or switch models: parakeet, sensevoice, whisper-small, whisper-large-v3-turbo
languagelist · select <code>List or switch transcription language — choices follow the active model
mcp—Run the MCP server on stdio
version · help—CLI version · usage

Results go to stdout, progress and errors to stderr — safe to pipe or redirect. --json always emits a single JSON object or array. whispernotes help prints the full usage; a misused command replies with its exact usage line. wn is a convenience alias — scripts and agents should call whispernotes, which always exists.

Privacy & security

  • Transport is a Unix domain socket at ~/Library/Application Support/WhisperNotes/api.sock with 0600 permissions — only your macOS user account can connect. No TCP port, no network interface, unreachable from any other machine.
  • Off by default: nothing is served until you enable the toggle in Settings.
  • MCP clients like Claude ask for your approval before each tool call.
  • Transcription runs on-device (Parakeet V3, Whisper, SenseVoice on the Neural Engine / MLX); results are stored only in your local history.

Links

License

The contents of this repository (documentation and metadata) are MIT-licensed. Whisper Notes itself — the application, including the embedded MCP server and CLI — is commercial software; see whispernotes.app for terms.

来源:README.md,提交 fbac2d2

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.2.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分