CrunchyMurmur
CrunchyMurmur logo

Press a shortcut. Speak.
Keep working.

Private-by-default voice dictation, meeting transcription, and Markdown notes for Windows, macOS, and Linux — with local Whisper transcription or optional cloud providers.

Download View on GitHub

Latest release All platforms MIT licensed

Install from the terminal 
> irm https://raw.githubusercontent.com/almoretti/CrunchyMurmur/main/install.ps1 | iex
$ curl -fsSL https://raw.githubusercontent.com/almoretti/CrunchyMurmur/main/install.sh | sh

The installer detects your OS and architecture, downloads the latest release, and verifies it against the published SHA-256 digest before installing.

CrunchyMurmur dashboard with dictation statistics and the recording overlay
CrunchyMurmur general settings in light mode
Appearance and device settings
CrunchyMurmur transcription engine settings
Local and cloud transcription
CrunchyMurmur notes workspace with folders, note list, and Markdown editor
Markdown notes workspace

What it does

Dictation anywhere

Hold the global shortcut, speak, and release to transcribe straight into the focused app.

Meeting capture

Record your microphone and, where supported, system audio as separate speaker-labelled tracks.

A real Markdown workspace

Edit notes, meeting notes, and reusable AI templates with write, split, and preview modes.

Local-first privacy

Use whisper.cpp fully offline. No account, no advertising SDK, no project-operated telemetry.

Useful progress, locally

Track dictated words, weighted words per minute, and consecutive active days on your device.

Verified releases and updates

Signed packages, checksums, SBOMs, provenance attestations, and stable in-app updates from GitHub Releases.

Choose where transcription happens

  • Local whisper.cpp — audio stays on your machine; no API key required.
  • Groq Whisper API — faster on many laptops; audio is sent to the Groq account you configure.
  • Optional AI formatting and notes — Anthropic, OpenAI, Groq, Claude Code, or Codex, only when you configure and invoke them.

In your language

The interface is available in 12 languages. It follows your system language by default, or pick one in Settings — changes apply instantly, no restart needed.

  • English
  • Italiano
  • Español
  • Português
  • Français
  • Deutsch
  • Dansk
  • Norsk
  • Svenska
  • 中文
  • 한국어
  • 日本語

Platform support

CrunchyMurmur shares its data model and most product features across Windows, macOS, and Linux. Native integrations intentionally differ where no reliable portable API exists.

CapabilityWindowsmacOSLinux
Dashboard, word count, WPM, streakSupportedSupportedSupported
Local whisper.cpp and Groq transcriptionSupportedSupportedSupported
AI formatting and AI Notes providersSupportedSupportedSupported
Notes, templates, recordings, retentionSupportedSupportedSupported
Localised interface (12 languages)SupportedSupportedSupported
Meeting microphone captureSupportedSupportedSupported
Meeting system/call audioSupportedSupported on macOS 13+Not currently supported
Speaker-labelled chunked transcriptionWhen both tracks existWhen both tracks existMicrophone labelled YOU
Default global shortcutHold Ctrl + WinHold FnConfigurable toggle
CalendarICS feedsNative EventKit and ICS feedsICS feeds
Automatic pasteNative input simulationAccessibility / Automationwtype or xdotool
PackagesNSIS x64 / ARM64Signed & notarized universal DMG / ZIPAppImage and Debian x64 / ARM64
UpdatesAutomaticAutomaticAppImage automatic; Debian reinstall

Designed for trust

  • No CrunchyMurmur account, analytics SDK, ads, or project-operated telemetry.
  • API keys use operating-system-backed safe storage when available.
  • Local data can be exported or permanently deleted from the app.
  • Audio retention never removes meeting transcripts or notes.
  • Release artifacts include SHA-256 checksums, an SPDX SBOM, and GitHub build-provenance attestations.

Documentation

Read the docs here on the site — rendered live from the GitHub repository, so they are always current.

Getting started

Install, pick a transcription engine, and make your first dictation.

Features and providers

Dictation, meetings, notes, the dashboard, and what each provider receives.

Platform support

The full capability matrix and Linux desktop requirements.

Updating

How automatic updates work and how to verify them.

Troubleshooting

Fix empty transcripts, permission issues, and engine mismatches.

Building from source

One-command source bootstraps and manual development setup.

Architecture

Process model, security boundaries, and how the pieces fit together.

All documentation →

The complete index, including the roadmap, project status, and release process.

Download

Packages are published on GitHub Releases with checksums and provenance attestations.

Prefer the terminal? The verified installer picks the right package for you. All downloads: github.com/almoretti/CrunchyMurmur/releases