Local Whisper MCP server
io.github.OrihuelaConde/local-whisper-mcp·v1.1.0Private audio and video transcription with Whisper on your own computer, on the GPU or CPU.
not scanned yet
0 stars
Reviews
Write oneNobody has reviewed Local Whisper yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Local Whisper tools
No tool declarations could be read from the package source. They show once the server is installed.
How Local Whisper compares
Against every graded Media MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 78% of 1,337 Media servers
Release history: 2 versions in the registry since 2026-10-09, latest 2026-11-04, typically one every 26 days.
Install Local Whisper in Claude Code, Cursor or VS Code
The registry entry has no remote endpoint or installable package.
What the publisher says
From the Local Whisper repository's README, as published. We do not edit it. Read it on GitHub
Local Whisper MCP
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.
Features
software. With ffmpeg on the PATH, it also reads M4A and FLAC.
- Transcribes WAV, Ogg Opus (WhatsApp and Telegram voice notes), and MP3 files with no extra
audio track and ignores the picture. Turn a recorded meeting or class into text or subtitles without extracting the audio first.
- Transcribes videos, such as MP4 and WebM files, when ffmpeg is installed: the server takes the
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.
- Runs on the GPU through Vulkan on Windows and Linux and through Metal on Apple Silicon, and falls
publishes, and frees its memory, including GPU memory, after 5 minutes without use.
- Downloads the model the first time it's needed, checks it against the hash that Hugging Face
and transcribes everything when background noise could hide quiet speech.
- Returns plain text, SubRip subtitles (SRT), or JSON segments with timestamps.
- Skips silence with voice activity detection on clean recordings, which keeps timestamps exact,
- Ships as one native executable per platform: there's no Python or .NET runtime to install.
Install
Download the files from the latest release. Each section below names the file it needs.
Claude Desktop
To add Local Whisper to Claude Desktop, install its extension:
local-whisper-mcp-VERSION-osx-arm64.mcpb for Apple Silicon Macs, or local-whisper-mcp-VERSION-osx-x64.mcpb for Intel Macs.
- Download the extension for your system: local-whisper-mcp-VERSION-win-x64.mcpb for Windows,
language.
- Open the file. Claude Desktop shows the extension's details.
- Click Install.
- Optional: In the extension's settings, choose the folders with your audio, the model, and the
Claude Code
To add Local Whisper to Claude Code, register the executable as an MCP server:
extract it to a folder that you keep.
- Download the archive for your system, such as local-whisper-mcp-VERSION-linux-x64.tar.gz, and
- Run the following command:
claude mcp add local-whisper -- PATH_TO_EXECUTABLEReplace PATHTOEXECUTABLE 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 LOCALWHISPERLANGUAGE=es -- PATHTOEXECUTABLE.
claude.ai chats on your computer
A claude.ai chat reaches the server through the Claude desktop app on your computer:
your computer under Run tasks on. The computer has to be on, with the Claude desktop app open.
- Install the extension in Claude Desktop, as described in Claude Desktop.
- When you start a chat in claude.ai, click + in the message box, choose Devices, and pick
folder, and the server deletes the copy after transcribing it.
- Attach the audio and ask Claude to transcribe it. Claude copies the file into the server's inbox
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, download local-whisper-skill.zip and upload it in Settings > Capabilities, under Skills.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Local Whisper: common questions
- Is Local Whisper MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the Local Whisper safety report
- Does Local Whisper need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Local Whisper maintained?
- The last commit was 26 days ago (2026-10-09). The latest release is v1.1.0.
- What can I use instead of Local Whisper?
- Servers from other publishers that do the same job: Transcription MCP server, FunASR MCP server and FFmpeg MCP server.
Alternatives to Local Whisper
Same job from other publishers: the closest match first, then the best rated.
- TranscriptionTranscribe audio and video and work with your transcript library from any AI app. 119 languages.not reviewedGrowingA
- FunASRTranscribe local audio with FunASR and SenseVoice using private, on-device inference.not reviewedEstablishedA
- FFmpegTrim, convert, resize, compress, and remix audio and video.not reviewedEstablishedA
Transloadit Media ProcessingProcess video, audio, images and documents with Transloadit Robots. Connect by URL with OAuth.not reviewedEstablishedA- anymdAny file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP.not reviewedEstablishedA