原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Local Whisper

作者:OrihuelaConde版本 1.1.0i★ 1i在你的电脑上运行代码仓库 ↗
注册名称io.github.OrihuelaConde/local-whisper-mcp

安装方法

What it does

Private audio and video transcription with Whisper on your own computer, on the GPU or CPU.

  • Connects 在你的电脑上运行
  • Account or key No key needed
  • Category 设计、图片与音频

可搭配使用

教 AI 做这类工作的 Skill,可与本项一起使用

impeccable

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

作者:pbakaus★ 113,0421 个 skill

Skill · 操作手册

diagram-design

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.

作者:cathrynlavery★ 68,2961 个 skill

Skill · 操作手册

frontend-slides

Create beautiful slides on the web using a coding agent's frontend skills

作者:zarazhangrui★ 32,5791 个 skill

Skill · 操作手册

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度4/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度12/1230 天内有发布或代码更新得满分
仍在响应0/8上次检查时云端端点有响应
使用分16/100

质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

通过 3/3 项检查 · 在你的电脑上运行

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude,但需要先准备

不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

  1. 下载开发者的安装文件

    下载作者的 .mcpb 文件

    .mcpb 文件直接来自开发者,我们没有修改

  2. 双击文件,然后在电脑版 Claude 应用中点击 Install

  3. 试一试

    用 Local Whisper 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 Local Whisper,或回答中出现 Local Whisper 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

ChatGPT 暂时无法连接 Local Whisper

Local Whisper 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器

你可以改用这些方式

A · 使用能连接 Local Whisper 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

B · 设计、图片与音频 类中能连接 ChatGPT 的其他服务器

从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的

Claude Code 暂时无法连接 Local Whisper

开发者只提供了电脑版 Claude 应用的安装文件

你可以改用这些方式

A · 使用能连接 Local Whisper 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

Cursor 暂时无法连接 Local Whisper

开发者只提供了电脑版 Claude 应用的安装文件

你可以改用这些方式

A · 使用能连接 Local Whisper 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

VS Code 暂时无法连接 Local Whisper

开发者只提供了电脑版 Claude 应用的安装文件

你可以改用这些方式

A · 使用能连接 Local Whisper 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Local Whisper 的人💬 讨论 →

一览

每周下载量i
不在 npm/PyPI 上
连接方式
在你的电脑上运行
最新版本i
1.1.0
发布到注册中心i
2026年11月4日
代码最后更新i
2026年11月10日
作者
OrihuelaConde
软件包
mcpb: …/local-whisper-mcp-1.1.0-win-x64.mcpb
mcpb: …/local-whisper-mcp-1.1.0-osx-arm64.mcpb
mcpb: …/local-whisper-mcp-1.1.0-osx-x64.mcpb
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

在你的电脑上运行,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 OrihuelaConde 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于10天前

  • ✓ 通过

    有许可证

    使用 MIT

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

已公开的漏洞(OSV.dev)

未检查:只能检查标明版本的 npm 和 PyPI 包

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/orihuelaconde-local-whisper-mcp.svg)](https://mcp.popnx.com/en/servers/orihuelaconde-local-whisper-mcp)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“设计、图片与音频”中的其他服务器比较i

  • 星标数多于此分类中其他 3313 个服务器的 79%
  • 发布到注册中心的时间比此分类中其他 3313 个服务器的 68% 更新
  • 基础检查结果等于或优于此分类中其他 3313 个服务器的 99%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Local Whisper 安全吗?

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于10天前,最新版本(1.1.0)于16天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。

有什么可以替代它?

同一分类中有:HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Pascal 3D Editor

Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.

作者:pascalorg广泛使用↓ 1037/周★ 2.6万 整个仓库的星标前天更新

电脑或云端✓ 服务方 · pascal.app

draw.io

Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.

作者:jgraph广泛使用★ 58543天前更新

在云端运行✓ 服务方 · draw.ioPopNx 团队已实际试用

Figma MCP Server

The Figma MCP server brings Figma design context directly into your AI workflow.

作者:figma广泛使用★ 221113个月前更新

在云端运行✓ 服务方 · mcp.figma.com
与相似项目对比
本项
Local Whisper
HyperFrames by HeyGenPascal 3D Editordraw.ioFigma MCP ServerRemocn: Remotion MCP server
运行位置需要安装在电脑上在云端运行,无需安装云端或安装在电脑上都可以在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否是否否是否
基础检查3/34/45/54/44/44/4
许可证MITApache-2.0MITApache-2.0–MIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Private, local audio transcription for Claude. Local Whisper is a Model Context Protocol (MCP) server that transcribes audio files with Whisper on your own computer, so voice notes, meetings, and lectures never leave it. It works in Claude Desktop, in Claude Code, and in claude.ai chats that run on your computer.

https://github.com/user-attachments/assets/dc71b178-b60d-457e-8f33-732696671c02

Features

  • Transcribes WAV, Ogg Opus (WhatsApp and Telegram voice notes), and MP3 files with no extra software. With ffmpeg on the PATH, it also reads M4A and FLAC.
  • Transcribes videos, such as MP4 and WebM files, when ffmpeg is installed: the server takes the audio track and ignores the picture. Turn a recorded meeting or class into text or subtitles without extracting the audio first.
  • Runs on the GPU through Vulkan on Windows and Linux and through Metal on Apple Silicon, and falls back to the CPU on its own. With the default model, large-v3-turbo-q8_0, an NVIDIA GeForce RTX 3080 transcribes a minute of audio in about one second.
  • Downloads the model the first time it's needed, checks it against the hash that Hugging Face publishes, and frees its memory, including GPU memory, after 5 minutes without use.
  • Returns plain text, SubRip subtitles (SRT), or JSON segments with timestamps.
  • Skips silence with voice activity detection on clean recordings, which keeps timestamps exact, and transcribes everything when background noise could hide quiet speech.
  • Ships as one native executable per platform: there's no Python or .NET runtime to install.

Install

Find your system in the following table, and download the file for the app where you use Claude. Each link downloads the file from the latest release.

SystemClaude DesktopClaude Code
Windows (x64)Download (.mcpb)Download (.zip)
macOS with Apple SiliconDownload (.mcpb)Download (.tar.gz)
macOS with an Intel processorDownload (.mcpb)Download (.tar.gz)
Linux (x64)Download (.mcpb)Download (.tar.gz)
Linux (arm64)Download (.mcpb)Download (.tar.gz)
Any system: the skill (optional)Download (.zip)Install the plugin

The skill tells Claude when and how to use the server. For more information, see The skill.

To check which Mac you have, choose Apple menu > About This Mac. A Chip line that starts with Apple, such as Apple M2, means Apple Silicon. A Processor line that names Intel means an Intel processor.

Claude Desktop for Linux is a beta for Ubuntu and Debian.

To verify a download, compare its SHA-256 hash with the one in SHA256SUMS.txt, on the releases page.

Claude Desktop

To add Local Whisper to Claude Desktop, install its extension:

  1. Download the extension for your system from the table in Install.
  2. Open the file. Claude Desktop shows the extension's details.
  3. Click Install.
  4. Optional: In the extension's settings, choose the folders with your audio, the model, and the language.
Claude Code

To add Local Whisper to Claude Code, register the executable as an MCP server:

  1. Download the archive for your system from the table in Install, and extract it to a folder that you keep.
  2. Run the following command:
   claude mcp add local-whisper -- PATH_TO_EXECUTABLE

Replace PATH_TO_EXECUTABLE with the full path of local-whisper-mcp (or local-whisper-mcp.exe on Windows) in that folder.

To change a setting, add it to the command as an environment variable, for example claude mcp add local-whisper -e LOCAL_WHISPER_LANGUAGE=es -- PATH_TO_EXECUTABLE.

claude.ai chats on your computer

A claude.ai chat reaches the server through the Claude desktop app on your computer:

  1. Install the extension in Claude Desktop, as described in Claude Desktop.
  2. When you start a chat in claude.ai, click + in the message box, choose Devices, and pick your computer under Run tasks on. The computer has to be on, with the Claude desktop app open.
  3. Attach the audio and ask Claude to transcribe it. Claude copies the file into the server's inbox folder, and the server deletes the copy after transcribing it.
The skill

The skill is optional, and recommended. The server works without it, but the skill tells Claude when to use the server, how to pass it a chat attachment, and what to tell you when the server isn't reachable. Without it, a claude.ai chat that doesn't run on your computer can't see the server and may try to transcribe the audio in the cloud instead of telling you how to connect it.

To add the skill to claude.ai and Claude Desktop, download local-whisper-skill.zip and upload it in Settings > Capabilities, under Skills.

To add the skill to Claude Code, install the local-whisper plugin from the orihuelaconde marketplace. First, add the marketplace:

claude plugin marketplace add OrihuelaConde/claude-plugins

Then install the plugin:

claude plugin install local-whisper@orihuelaconde

The plugin carries only the skill; register the server as described in Claude Code.

Use

Ask Claude in your own words. For example:

  • "Transcribe the voice note I just attached."
  • "Transcribe C:\Users\me\Recordings\meeting.m4a and summarize the decisions."
  • "Make Spanish subtitles for ~/Videos/class.mp4."
  • "Transcribe the interview with Mirtha Legrand from her lunch show."

Video files are much larger than audio files. When a video is already on your computer, give Claude its path instead of attaching it to the chat, so it doesn't have to travel through the chat and back.

The server provides three tools:

ToolWhat it does
transcribeTranscribes an audio or video file. Its parameters are path (absolute), model, language, format (txt, srt, or json), vad, and hints.
statusReports the device in use, the installed models and their sizes, downloads in progress, the inbox, the allowed folders, and the log folder.
delete_modelsDeletes downloaded models to free disk space. Its description tells Claude to confirm with you first.

When you name the people, places, or products in a recording, Claude can pass up to about eight of them to transcribe as hints, and Whisper spells them the way you wrote them. Hints help most with uncommon names, which Whisper otherwise spells by ear. The server takes hints from version 1.1.0.

Configure

The Claude Desktop extension shows these settings on its page. For Claude Code and other MCP clients, set them as environment variables:

VariableDefaultDescription
LOCAL_WHISPER_MODELlarge-v3-turbo-q8_0Any model from whisper.cpp's model list, by name (base) or file name (ggml-base.bin).
LOCAL_WHISPER_LANGUAGEautoA language code such as en or es, or auto to detect it.
LOCAL_WHISPER_USE_GPUtruefalse runs only on the CPU.
LOCAL_WHISPER_RUNTIMEautoauto, cpu, or vulkan. A runtime that can't load falls back to the CPU.
LOCAL_WHISPER_IDLE_MINUTES5Minutes without use before the model leaves memory. 0 frees it after every transcription.
LOCAL_WHISPER_ALLOWED_ROOTSYour user folderFolders the server may read audio from, separated by ; on Windows and : elsewhere. The --allowed-roots DIR... option replaces it.
LOCAL_WHISPER_INBOX_DIR~/.local-whisper-mcp/inboxFolder for audio that clients copy to the computer. The server deletes each file there after transcribing it.
LOCAL_WHISPER_MODELS_DIR~/.local-whisper-mcp/modelsFolder for the downloaded models.
LOCAL_WHISPER_AUTO_DOWNLOADtruefalse stops the server from downloading missing models.
LOCAL_WHISPER_THREADSUp to 8CPU threads for transcription.
LOCAL_WHISPER_FFMPEGFound automaticallyFull path of the ffmpeg executable. Without it, the server looks on the PATH and in the folders of winget, Scoop, Chocolatey, Homebrew, and MacPorts.

To download a model before its first use, for example on a slow connection, run the executable with the download command:

local-whisper-mcp download large-v3-turbo-q8_0

Privacy

  • Transcription runs on your computer. The server goes online only to download models from Hugging Face, which you can turn off with LOCAL_WHISPER_AUTO_DOWNLOAD=false.
  • The server reads audio only inside the allowed folders and the inbox, and it deletes only files in the inbox: each one after transcribing it, and any left there for more than a day.
  • The log in ~/.local-whisper-mcp/logs records timings, settings, and errors, never transcripts. Routine entries leave out file names, but an error entry can include the path of the file that failed, so review the log before you share it. The server keeps a week of logs.

Requirements

  • Windows 10 or later (x64), macOS (Apple Silicon or Intel), or Linux (x64 or arm64).
  • On x64, a processor with AVX2.
  • For the GPU: a Vulkan driver on Windows and Linux x64, or Apple Silicon for Metal. Without one, the server uses the CPU.
  • On Linux, the OpenMP runtime: sudo apt install libgomp1 on Debian and Ubuntu.
  • Optional: ffmpeg, for formats other than WAV, Ogg Opus, and MP3.

The release files aren't signed. On macOS, if Gatekeeper blocks the executable from the archive, allow it with xattr -dr com.apple.quarantine FOLDER, where FOLDER is the extracted folder.

Troubleshoot

  • The first transcription takes minutes. The server is downloading the model, about 900 MB for the default one. Claude can follow the download with the status tool.
  • The first transcription on a Mac with Apple Silicon takes about 15 seconds more. macOS compiles the GPU shaders once per computer.
  • **Parts of a recording

只显示了开头部分;其余内容请在仓库中阅读