Murmure is a privacy-first, open-source speech-to-text application designed for fully local and private voice transcription. It leverages NVIDIA’s Parakeet TDT 0.6B v3 model to enable fast, on-device processing without requiring an internet connection or data collection.
Key Features:
Privacy-Focused: All processing occurs locally, ensuring no data leaves your device.
Multilingual Support: Offers transcription in 25 European languages, including English, French, German, Spanish, and more.
On-Device AI: Utilizes NVIDIA’s Parakeet model for efficient and low-latency speech recognition.
Local LLM Post-Processing: Enhances transcriptions through grammar correction and translation using local language models.
Cross-Platform Availability: Runs seamlessly on Windows, Linux, and macOS, ensuring broad accessibility.
Open Source: Built with transparency and customization in mind under the AGPL-3.0 license.
Audience & Benefit:
Ideal for writers, content creators, educators, developers integrating speech features into projects, and anyone prioritizing data privacy. Murmure enables hands-free note-taking, creative dictation, and seamless integration of speech-to-text functionality without compromising on privacy or performance.
Installation is straightforward via winget, making it accessible to a wide range of users across supported platforms.
README
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.
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)
> [!IMPORTANT]
> Murmure requires Windows 10 or later. Older versions (such as Windows 8.1) are not supported and may result in missing system libraries (e.g. dxcore.dll).
Multiple installation methods are available:
Using a .msi or setup.exe file:
Go to the release page and download the latest Murmure_x64.msi (or Murmure_x64-setup.exe).
Run the installer and follow the setup wizard.
Via WinGet:
Open the Console app via the Windows start menu.
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)
> [!NOTE]
> Wayland: Two shortcut modes are available. KDE Plasma 6, Hyprland, and Sway use the xdg-desktop-portal GlobalShortcuts portal with no manual setup. GNOME defaults to CLI mode: you must configure a custom OS shortcut before using Murmure, and Push-to-talk is not available. See the Linux installation guide and the shortcut configuration guide.
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):
Go to the release page and download the latest Murmure_amd64.deb.
Install it: sudo dpkg -i Murmure_amd64.deb
Using an AppImage:
Download Murmure_amd64.AppImage from the release page.
Make it executable: chmod +x Murmure_amd64.AppImage
Run the AppImage.
MacOS (Official)
Download Murmure_aarch64_darwin.dmg from the release page
Drag Murmure to the Applications folder, then open it from there.
Murmure should ask for permissions to access your microphone and accessibility.
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) :
Remove Murmure from System Settings → Privacy & Security → Accessibility.
Remove Murmure from System Settings → Privacy & Security → Input monitoring.
Install the last version
Launch Murmure.
Re-grant the Accessibility
Re-grant the Input monitoring permission
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)
Download Murmure_x86_64_darwin.dmg from the release page
Drag Murmure to the Applications folder, then open it from there.
Murmure should ask for permissions to access your microphone and accessibility.
Restart Murmure for the permissions to take effect.
The same upgrade note from 1.6.0 applies. See the MacOS section above.
CLI Import (1.8.0)
Murmure supports importing a .murmure configuration file via the command line (murmure import config.murmure), useful for mass deployment or sharing settings across machines. A --strategy merge option is available to keep existing settings. See the CLI documentation for details.
fix(macos): Reopen the main window when the Dock icon is clicked, closing the window only hides it so the click did nothing and the menu bar entry was the only way back to the UI (thank you @linkermaxx) https://github.com/Kieirra/murmure/pull/439
fix(audio): Restore the output streams that were recreated or started while dictating, browsers drop and recreate their stream when tabs change so the restore missed them and the audio server kept the lowered level for the whole application, which made every new tab start at that level
fix(transcription): Turn the hesitation sounds cleanup into an option, off by default, the list is stripped whatever the language so it also deletes real words such as the German "um" https://github.com/Kieirra/murmure/issues/445
fix(macos): Explain in the Show in Dock setting that keeping the Dock icon hides the recording overlay over full-screen apps, macOS ties that switch to the activation policy and a Regular app cannot join the Space owned by another full-screen app whatever the window asks for https://github.com/Kieirra/murmure/issues/437
fix(overlay): Set the collection behavior on the recording overlay at creation time on macOS, only the window level is set today so following Spaces works by default rather than by design https://github.com/Kieirra/murmure/issues/437
feat(cli): Add a --quit flag to close Murmure completely from the command line, the tray menu is the only way today so tiling WM users have no keyboard path https://github.com/Kieirra/murmure/issues/429
feat(overlay): Keep the overlay on screen after a dictation with the transcription and a copy button, plus a thin bar showing the time left before it hides, so you see what was written when the paste landed nowhere and you can read the result of a command without pasting it, no focus detection needed so it works on the three platforms https://github.com/Kieirra/murmure/discussions/443
feat(settings): Add an automatic insert option next to the text insertion mode, to keep an insertion method (Ctrl+V, Ctrl+Shift+V, Direct) while turning off the automatic insertion of the transcript https://github.com/Kieirra/murmure/issues/449
fix(api): Remove the experimental tag and consolidate the API
fix(api): Implement LLM Connect service
Backlog
feat(updater): Opt-in setting to subscribe to beta (pre-release) updates
(under consideration) feat(draft): Draft Mode to review and edit a transcription before writing (medical use case)
(under consideration) fix(packaging): Authenticode-sign the inner murmure.exe on Windows, not only the installers, so the app runs under Smart App Control (needs a second SignPath submission before bundling) https://github.com/Kieirra/murmure/issues/428
<img src="https://signpath.org/assets/favicon-50x50.png" width="40" />
Free code signing on Windows provided by <a href="https://about.signpath.io/">SignPath.io</a>, certificate by <a href="https://signpath.org/">SignPath Foundation</a>
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.
