1.11.1 (beta)

Beta release for testers. Not auto-distributed via updater or WinGet.

Test plan and feedback: #419

1.10.1

Murmure 1.10.1

A big update on Murmure's core features, with a strong focus on speed, accuracy, and a smarter dictionary.

Faster

Murmure now splits your recording on natural pauses and transcribes each part in the background while you keep talking, so long dictations finish much faster and the old 5 minute limit is gone.

More accurate

A brand new AI model (thanks @thiswillbeyourgithub) brings noticeably better accuracy and far fewer unwanted switches to English. It works together with a reworked audio pipeline that prepares your voice with higher quality resampling before it reaches the model, which also helps a lot on low-end microphones.

Smarter dictionary

The dictionary has been redesigned around a completely new approach. Your custom words are now boosted directly inside the model's decoding, so they get recognised far more reliably than before.

Also new

• A new murmure command to transcribe audio files from the terminal.
• UI improvements across the app, plus monochrome tray icons on Linux and macOS.
• A close button on the overlay to cancel an ongoing transcription.

Fixes

• Smoother recordings on Linux, no more crackling on some setups.
• macOS click-through and cancel button now work correctly.
• Bluetooth headsets no longer stay active between recordings.
• Several shortcut fixes, including duplicates and Ctrl only shortcuts.
• Security updates for dependencies.

🙏 Thanks

• Beta testers: @HachetAmaury, Walden, CollectifWeb
• Contributors: @thiswillbeyourgithub, @flomillot, @blouflab
• Donors: Ubertartine, Chase, Gizmo38, Aparrot, Raphael, Stephen Berard, B0g, AndraaX, Prometee, scwall, thomasdiluccio

See full CHANGELOG.

1.9.0

Murmure 1.9.0

This release brings a major overlay overhaul, native Wayland support on Linux, and Smart Speech Mic to turn your phone into a wireless microphone, plus a new RPM bundle for Fedora and many fixes.

New Features

• (Major) Smart Speech Mic — Use your phone as a wireless microphone by scanning a QR code in Murmure, no app install needed on the phone.
• (Major) Native Wayland support on Linux via CLI (thanks @BorisLord).
• (Major) Overlay overhaul — Configurable overlay size, real-time streaming preview with configurable text width, font size and max lines, and a color-coded visualizer per recording mode (standard, LLM, command).
• Documentation — Official Murmure documentation site (configuration, limitations, tips): https://kieirra.github.io/murmure/
• Tray — Recording indicator on the tray icon during transcription (visible even when the overlay is hidden); copy the last transcript directly from the tray menu.
• Shortcuts — Shortcut to toggle Voice Mode on/off (#279); Ctrl+Shift+1-4 now directly trigger LLM transcription with the matching prompt; hide the LLM Connect shortcut when the feature is disabled.
• Layout — New Extensions section in the menu; global UX/UI optimization to simplify the interface.
• Linux — RPM bundle for Fedora-based distributions (thanks @BorisLord).
• Rules / Dictionary / Import-Export — Custom names for personal formatting rules; warn when entering digits in a dictionary entry; include Voice Mode and Smart Mic categories in import/export.

Bug Fixes

• Overlay — Error messages no longer disappear too quickly and block subsequent recordings; fixed streaming auto-scroll.
• Overlay (Linux) — Recording overlay is no longer focusable, preventing focus theft (thanks @flomillot) (#344).
• macOS — Fixed auto-update (#301); Cancel shortcut (Escape) no longer blocks other apps when not recording (#302); tray icon adapts to light/dark mode (thanks @fwehrling); left click on the tray icon opens the menu.
• Voice Mode — Wake word now detected when spoken mid-sentence without a pause.
• Shortcuts — Some AZERTY keys (e.g. ²) could not be bound; clarified LLM Connect vs Command shortcut descriptions.
• Linux / Wayland — Disabled Smart Mic and push-to-talk on Wayland; changed the default Cancel shortcut on Wayland.
• Sidebar / Audio / Visualizer / Logs — Fixed sidebar disappearing on high-scaling displays; first start/stop sound after a cold start; more sensitive visualizer for low-gain microphones; log time displayed in the correct timezone.

Performance

• Shrunk Rust binary by 32% (66 MB to 45 MB) and trimmed unused dependencies (thanks @BorisLord) (#310).
• Skip Ollama warmup when the model is already loaded (thanks @BorisLord) (#324).

🙏 Thanks

• Beta testers (discussion #346): @laurentkempe, @Zabalero, @thiswillbeyourgithub, @anouar-coscientia, @tomsquest
• Contributors: @BorisLord, @fwehrling, @flomillot, @dadoonet
• Donors: @scwall, @stefounet, @Morpheus9057, @PaulMLH, @aparrot89, gizmo38, chase-14, floflow-3, migraine, ubertartine, b0g-3, frédéric-1477, madinia-1, sylvain-1123

See full CHANGELOG.

1.8.1

Murmure 1.8.1

This patch release fixes a critical issue on macOS where shortcuts (including Space) were not detected, along with several smaller fixes.

---

Bug Fixes

• (macOS) Fix shortcuts not working - Space and other shortcuts were not detected on macOS. Replaced rdev event listener with polling-based approach.
• Remove Ctrl+B shortcut that could hide sidebar (#266).
• Allow virtual microphones in device list, e.g. Nvidia Broadcast (#164).
• Add beta tag and CPU usage warning for Voice Mode.
• Security updates for dependencies.

---

See full CHANGELOG.

1.8.0

Murmure 1.8.0

This release introduces Voice Mode, a hands-free way to control Murmure using wake words, no keyboard needed. It also brings remote LLM server support, full settings import/export with CLI support, and dozens of improvements across shortcuts, rules, and the overall experience.

---

New Features

• (Major) Voice Mode: Activate Murmure by voice with customizable wake words, no keyboard needed. Includes auto-send enter, and wake word listener stays active during keyboard-triggered recording. (#178, #187)

• (Major) LLM Remote Servers: Connect to remote OpenAI-compatible API servers for LLM Connect, with per-mode provider switching, model search, per-mode voice triggers, and onboarding flow. (#197, #206)

• (Major) Import/Export Settings: Import and export configuration settings partially or fully. Add CLI import support (murmure import <file>) for sysadmin mass deployment. (#212, #223)

• Shortcuts: Add support for mouse buttons, OEM keys (-, =, [, ], ;, ', etc.), <>, F13-F24. Add a shortcut in overlay to cancel recording. (#158, #194, #218, #161)

• Rules: Add regex support for custom rules, improve rule labels, add "?" helper for replacement text, short text correction (auto-lowercase/remove punctuation), and rule reordering. (#163, #168, #195, #170)

• LLM: Allow LLM mode reordering. Add "Voice Dictation" preset for interpreting spoken formatting commands as typographic characters. (#180)

• Dictionary: Add option to clear all dictionary entries. (#159)

• About Page: Redesigned with starry background and sponsor cards. (#198)

• Autostart: Start minimized to tray on autostart. (#201)

• macOS: Add configurable option to show/hide application in Dock. (#226)

• Linux: Add .deb package and install.sh one-liner script for Debian/Ubuntu. (#174)

• Update: Update tauri-plugin-updater to 2.10.0 for multi-format support (.deb, .exe, macOS Intel).

• Sidebar: Add "Release notes" link in sidebar footer.

• Defaults: Improve default settings for new users (transcription in RAM, trailing space). (#187)

---

Bug Fixes

• Fix overlay scrollbar on Windows (#169), overlay stealing focus (#177), overlay freeze on audio timeout (#252).
• Fix double percentage display during download.
• Use dark mode colors consistently. (#199)
• Improve microphone list and keep manually selected device when disconnected (#204). Fix crash when no microphone is available (#217).
• Improve LLM accuracy with system prompts. Improve response speed of reasoning models by disabling thinking mode. (#213)
• Improve smart mode auto-spacing and word deduplication (parakeet fix). (#219)
• Fix selected text detection when clipboard already contains the same content. (#229)
• Fix ToggleToTalk accidental restart caused by X11 auto-repeat.
• Fix spurious modifier key release on macOS after paste and recording lock management. (#241)
• Fix wake word language-aware validation, history update, and EMA smoothing for VAD.

---

Thanks

Thanks to all contributors, testers, and supporters who made this release possible:

Contributors: @MissonHxC @thiswillbeyourgithub @buffalodebile @Prinzhorn @diodiogod

Beta testers: @ivan-pourmir @icristescu @laurentkempe @OlafausBerlin @HachetAmaury @KevinGeorge, Aparrot

Tippers: Aparrot, Davidda, djvu, Gizmo38, IiPo, Jérémy, Mablunt, Mactin, Arnaud, Guy, Alain, FloB, Francis, Richard Edward, @scwall

---

See full CHANGELOG.

1.7.0

🚀 Murmure 1.7.0 — February 12, 2026

This release pushes Murmure further into the LLM-powered workflow era, with powerful text manipulation features, improved customization, and stronger security foundations.

But 1.7.0 also goes further on what truly defines Murmure: privacy by design.
Temporary audio is now stored in the system tmp directory for automatic OS‑level cleanup, even in case of a crash. The new logging system avoids exposing transcriptions by default, and automated security scanning (SonarQube) has been introduced to further strengthen code integrity.

Finally, both the macOS and Windows versions are now officially signed. Windows may still display reputation warnings initially, as the certificate builds trust over time.

---

✨ New Features

• (Major) Select Command — Select any text and transform it using a custom command (fix grammar, translate to English, rephrase, etc.). Murmure now works as a contextual AI editor, not just a speech‑to‑text tool.

• (Major) LLM Prompts — Multiple saved prompts with:

  • Syntax highlighting in the prompt editor
  • Anchor tags enforcement for safer output control
  • New “Cursor Developer” preset

• Input Microphone Selection — Choose your preferred input microphone directly in Settings. Thanks to @litel-fr.

• Dictionary Import / Export — Import and export custom words, including medical presets. Thanks to @icristescu (#72]).

• Text Insertion Mode — Choose how text is inserted:

  • Standard mode
  • Terminal-compatible mode
  • Direct typing mode
    (#119])

• Log Verbosity Controls — Configure log levels (trace, debug, info, warn, error) and quickly open the logs folder from the app.

• macOS: Improved global shortcut handling — no longer limited by system-reserved shortcuts (Thanks to @HachetAmaury)

---

🐛 Bug Fixes

• Fixed fullscreen issue on Select Model page on macOS (#82]).
• Transcriptions are no longer logged by default for improved privacy (#88]).
• Temporary audio files are now saved in the system tmp folder instead of app_dir in case of crash ([#88](#88)).
• Fixed invalid word format error message in dictionary.
• Allow digit conversion threshold to be set to 0.
• Updated dependencies to resolve security vulnerabilities.

---

♻️ Refactor

• Resolved major SonarQube issues.
• Streamlined shortcut logic and optimized event lookup for better maintainability and performance.

---

🔧 CI & Security

• Added Security Scanning with SonarQube.
• Improved static analysis for contributions (tests, compilation, linting, etc.).
• Windows NSIS (.exe) installer now runs without requiring administrator privileges.

---

📜 License Update

Murmure is now released under the GNU AGPL v3 instead of the GPL v3.
This change strengthens the project’s commitment to open-source principles by ensuring that any network‑accessible modifications must also remain open source.

---

Murmure 1.7.0 strengthens its position as a privacy-first, local AI companion, combining speech recognition, contextual editing, and LLM workflows — all running on your machine.

🙌 Thanks to all contributors and testers who continue to make Murmure better with every release. @HachetAmaury @laurentkempe @thiswillbeyourgithub @stevebeauge @vclerc @icristescu @litel-fr

1.6.0

✨ New Features

• (Major) LLM Connect — Connect Murmure to a local LLM (Ollama) to enhance, correct, or reformat transcriptions through post‑processing. Includes presets for translation, medical dictation, development, and automatic reformulation.
• (Major) Formatting Rules — Automatic text transformations: add trailing spaces, insert spaces before ?!, convert text-to-numbers, or apply custom find/replace rules.
• Toggle-to-Talk Mode — New alternative to push‑to‑talk: press once to start recording, press again to stop. Thanks to @nicolascrop.
• Sound Feedback — Audio cues when starting and stopping a recording.

♻️ Refactor

• Improved UI notifications.
• Backend refactor aligned with SRP principles.
• Dictionary configuration migration in preparation for import/export support. Thanks to @icristescu.

🐛 Bug Fixes

• Fixed overlay misalignment with fractional display scaling. Thanks to @flomillot (PR #73).
• Fixed a transcription pipeline issue where processing would stop when the transcription was empty, preventing dictionary rules, formatting rules, and LLM post‑processing from being triggered.

🧪 Experimental

• Added an experimental macOS build (Intel architecture only).

🙌 Thanks

Special thanks to our beta testers: @HachetAmaury, @Grujowmi, and @aparrot.

1.5.0

✨ New Features
- Display words per minute, MB saved (no cloud), and total words statistics
- MacOS version support
- Option to not make the last transcription persistent in history and remove it at each shutdown
- FR/EN translation of the application
- Add onboarding tutorial for first time users

🐛 Bug Fixes
- Prevent menu from scrolling on long pages
- Restart application after uploading to new version
- Display the overlay on the active screen

1.4.0

What's Changed

🐛 Bug Fixes
- Second transcription losing cursor focus and sometimes not working properly.
- Minor UI change on long shortcut in Settings

✨ New Features
- Click on history, save it in clipboard
- Add a button to clear transcription history
- Add option in Settings to keep the transcription in clipboard

New Contributors

• @Horgix made their first contribution in #16
• @mmichelot made their first contribution in #17

Full Changelog: 1.3.0...1.4.0

1.3.0

🐛 Bug Fixes

• Fixed small memory leak
• Fixed the unwanted "v" key activation when assigning shortcuts
• Corrected the GitHub link

✨ New Features

• Added an experimental API allowing Murmure to connect with external software
  (can be enabled in Settings → System)
• Improved shortcut UI for better usability
• Removed the experimental tag for the Linux AppImage. It now works identically to the Windows version (users who had the experimental version need to reinstall it to benefit from the "check for updates" feature)