Murmure

A privacy-first, open-source speech-to-text application that runs entirely on your machine, powered by a neural network via NVIDIA’s Parakeet TDT 0.6B v3 model for fast, local transcription. Murmure turns your voice into text with no internet connection and zero data collection, and supports 25 European languages.

Learn more on the official website.

Table of Contents

• Features
• Usage
• Installation
  • Windows (Official)
  • Linux (Official)
  • MacOS (Official)
  • MacOS - Intel (Official)
• CLI Import (1.8.0)
• Changelog
• 🗺️ Roadmap
• Contributing
• Privacy Policy
• Sponsors
• Support Development
• License
• Acknowledgments

Features

• Privacy First: All processing happens locally on your device. No data ever leaves your computer.
• No Telemetry: Zero tracking, zero analytics. Your data stays yours, always.
• Open Source: Free and open source software. Inspect, modify, and contribute.
• Powered by Parakeet TDT 0.6B v3: NVIDIA’s latest state-of-the-art speech recognition model runs entirely on-device for fast, low-latency transcription.
• Multilingual: Supports 25 languages!

List of supported languages

Bulgarian (bg), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Finnish (fi), French (fr), German (de), Greek (el), Hungarian (hu), Italian (it), Latvian (lv), Lithuanian (lt), Maltese (mt), Polish (pl), Portuguese (pt), Romanian (ro), Slovak (sk), Slovenian (sl), Spanish (es), Swedish (sv), Russian (ru), Ukrainian (uk)

Usage

Murmure provides a clean and focused speech-to-text experience. Once launched, simply start recording your voice. The text appears instantly, processed directly on your computer.

Typical use cases include:

• Dictating to any AI prompt (Cursor, ChatGPT, Mistral, Claude code, etc.)
• Writing notes hands-free
• Capturing creative ideas or dictation
• Post processing with a local LLM to translate, fix grammar, etc.

Because all computation is local, no network connection is required.

Installation

Windows (Official)

Multiple installation methods are available:

• Using a .msi or setup.exe file:

  1. Go to the release page and download the latest Murmure_x64.msi (or Murmure_x64-setup.exe).
  2. Run the installer and follow the setup wizard.

• Via WinGet:

  1. Open the Console app via the Windows start menu.
  2. Inside the console, paste winget install Kieirra.Murmure and follow the instructions. (--scope user will be available in the future)

Important

Murmure requires the Microsoft Visual C++ Redistributable to work on Windows. This package is present on most computers, but if you encounter the error message The code execution cannot proceed because MSVCP140.dll was not found. Reinstalling the program may fix this problem., download and install the package from the official page or use this direct download link: https://aka.ms/vc14/vc_redist.x64.exe

⚠️ Antivirus Notice : Some users reported that Kaspersky may block Murmure. If needed, please add Murmure as an exclusion in your antivirus settings.

Linux (Official)

Multiple installation methods are available:

• Quick install via terminal (Debian-based distributions):

  curl -fsSL https://raw.githubusercontent.com/Kieirra/murmure/main/install.sh | sh

• Using a .deb file (Debian-based distributions):

  1. Go to the release page and download the latest Murmure_amd64.deb.
  2. Install it: sudo dpkg -i Murmure_amd64.deb

• Using an AppImage:

  1. Download Murmure_amd64.AppImage from the release page.
  2. Make it executable: chmod +x Murmure_amd64.AppImage
  3. Run the AppImage.

Important

Murmure currently has limited support on Wayland-based distributions (except Fedora, which can fall back to X11 for some apps).
This appears to be related to Wayland’s sandbox restrictions for AppImages, the global shortcut to start recording will not work in this environment.
No workaround is available yet. See #28

MacOS (Official)

1. Download Murmure_aarch64_darwin.dmg from the release page
2. Drag Murmure to the Applications folder, then open it from there.
3. Murmure should ask for permissions to access your microphone and accessibility.
4. Restart Murmure for the permissions to take effect.

Important

Updating Murmure on macOS from 1.6.0: If you experience issues with Murmure and the shortcuts are not working, please do this exactly in this order, (and "Remove" means not only un-toggling but really removing completely Murmure from the list) :

1. Remove Murmure from System Settings → Privacy & Security → Accessibility.
2. Remove Murmure from System Settings → Privacy & Security → Input monitoring.
3. Install the last version
4. Launch Murmure.
5. Re-grant the Accessibility
6. Re-grant the Input monitoring permission
7. Restart Murmure.

it should work. It's a bit painful but you will not do it again with the next version, it's because 1.6.0 have the same name but is not detected as the same application... so macos is lost.

MacOS - Intel (Official)

1. Download Murmure_x86_64_darwin.dmg from the release page
2. Drag Murmure to the Applications folder, then open it from there.
3. Murmure should ask for permissions to access your microphone and accessibility.
4. Restart Murmure for the permissions to take effect.

Important

Updating Murmure on macOS from 1.6.0: If you experience issues with Murmure and the shortcuts are not working, please do this exactly in this order, (and "Remove" means not only un-toggling but really removing completely Murmure from the list) :

1. Remove Murmure from System Settings → Privacy & Security → Accessibility.
2. Remove Murmure from System Settings → Privacy & Security → Input monitoring.
3. Install the last version
4. Launch Murmure.
5. Re-grant the Accessibility
6. Re-grant the Input monitoring permission
7. Restart Murmure.

it should work. It's a bit painful but you will not do it again with the next version, it's because 1.6.0 have the same name but is not detected as the same application... so macos is lost.

CLI Import (1.8.0)

Note

This feature is available starting from version 1.8.0, which is currently in beta testing. It is not available in the current stable release (1.7.0).

Murmure supports importing a .murmure configuration file via the command line, useful for sysadmin mass deployment or sharing settings across machines.

Linux:

murmure import config.murmure

macOS:

/Applications/murmure.app/Contents/MacOS/murmure import config.murmure

Windows:

murmure.exe import config.murmure

You can also specify an import strategy (replace by default, or merge to keep existing settings and add new ones):

murmure import config.murmure --strategy merge

For more details, run murmure import --help.

Changelog

See CHANGELOG.md.

🗺️ Roadmap

• (1.8.0) MAJOR feat(voice-mode): Add voice activation (voice mode) to trigger Murmure without keyboard shortcuts #178 #171
• (1.8.0) MAJOR feat(llm): Add remote server support for LLM Connect (OpenAI-compatible API, per-mode provider switching, onboarding flow)
• (1.8.0) MAJOR feat(settings): Import/Export settings partially or fully
• (1.8.0) feat(voice-mode): Add auto-send enter with voice mode (#156)
• (1.8.0) feat(voice-mode): Wake word listener stays active: validate/cancel words work during keyboard-triggered recording
• (1.8.0) feat(shortcuts): Add support for mouse buttons (#158)
• (1.8.0) feat(dictionary): Add an option to clear all dictionary entries (#159)
• (1.8.0) feat(shortcuts): Add a shortcut in overlay to cancel recording #161
• (1.8.0) feat(rules): Add regex support for custom rules #163 #105
• (1.8.0) feat(rules): Improve rules label to make sentences #163 #101
• (1.8.0) feat(rules): Add a “?” helper in the “Replacement text” field (explain natural language input and real line breaks instead of \n) #163
• (1.8.0) feat(rules): Short text correction — auto-lowercase and remove trailing punctuation for short transcriptions (1-2 words)
• (1.8.0) feat(rules): Allow rule reordering #170
• (1.8.0) fix(overlay): remove scrollbar on some configurations on windows #169
• (1.8.0) feat(ci): Add a .deb package and install.sh one-liner script for Debian/Ubuntu/Linux Mint
• (1.8.0) feat(update): Update tauri-plugin-updater to 2.10.0 for multi-format support (.deb, .exe, macOS Intel)
• (1.8.0) fix(update): Fix double percentage display during download
• (1.8.0) feat(sidebar): Add "Release notes" link in sidebar footer
• (1.8.0) fix(overlay): Prevent overlay from stealing window focus on show
• (1.8.0) feat(llm): Allow llm mode reordering #104
• (1.8.0) feat(settings): Improve default settings for new user (transcription in RAM, trailing space after each transcription)
• (1.8.0) feat(shortcuts): Add support for <>, ², F13-F24 #194 #189
• (1.8.0) feat(about): Improve About page UI #198
• (1.8.0) fix(ui): Use dark mode colors consistently
• (1.8.0) feat(autostart): start minimized to tray on autostart #201
• (1.8.0) fix(settings): improve microphone list and keep manually selected device when disconnected
• (1.8.0) fix(llm-connect): Improve the accuracy and instruction-following capabilities of local LLMs by using system prompts.
• (1.8.0) fix(llm-connect): Significantly improve the response speed of reasoning models by disabling thinking mode. (Qwen 3.5, Ministral, etc.)
• (1.8.0) fix(settings): Crash when no microphone is available
• (1.8.0) feat(cli): Add CLI import support (murmure import <file>) for sysadmin mass deployment
• (1.8.0) feat(shortcuts): Add support for OEM keys (-, =, [, ], ;, ', ,, ., /, ) and fix digit row on all keyboard layouts
• (1.8.0) fix(rules): Improve smart mode auto-spacing and add word deduplication (parakeet fix)
• fix(command): Fix selected text detection when clipboard already contains the same content
• feat(shortcuts): using delete should remove shortcuts
• fix(shortcuts): Do not allow adding duplicate shortcuts
• feat(dictionary): Virtualize dictionary to handle large dictionaries
• feat(llm): Automatically detect Ollama at first LLM Connect tutorial.
• feat(overlay): Configure overlay size
• feat(overlay): Allow dragging the overlay to change its position #64
• feat(dictionary): Improve detection #44
• fix(visualizer): Adjust sensitivity (dynamic or lower)
• fix(visualizer): Visualizer does not always reset at the end of a transcription
• refactor(settings): Secure settings persistence (migrate to tauri-plugin-store for atomic writes)
• feat(shortcuts): Add a shortcut to automatically add a selected word to the dictionary (copy selection → read word → add to dictionary)
• (under consideration) feat(advanced): Audio pre-prompt #75
• (under consideration) feat(webhook): Send an HTTP request after CTRL + SPACE (opens up many interesting possibilities)

Contributing

See CONTRIBUTING.md.

Reporting issues is done on GitHub.

Privacy Policy

See PRIVACY_POLICY.md.

Sponsors

Free code signing on Windows provided by SignPath.io, certificate by SignPath Foundation

Support Development

If you like Murmure and want to support its development: Support on Tipeee

License

Murmure is free and open source, released under the GNU AGPL v3 License. You can inspect, modify, and redistribute it freely as long as derivative works remain open source.

Acknowledgments

• Thanks to NVIDIA for releasing the model Parakeet TDT 0.6B v3
• Tauri for being an amazing tool
• The open‑source community for their tools and libraries.