Skip to content
Blurt
Download for Mac

Changelog

RSS

What changed

Updates are free on every plan. 1.2.1 never shipped on its own — 1.2.0 went straight to 1.2.2. Releases before 1.2.0 shipped without written notes, so they are not listed rather than reconstructed after the fact.

1.2.5

Added

  • A one-time prompt asking whether to share anonymous usage counts: after the first-run tour on new installs, or at launch on updated ones. Sharing stays off unless you choose it, and either answer is remembered.

Changed

  • The tour's welcome text now says audio and text never leave the device, which is more exact than the old wording.

1.2.4

Changed

  • Lower idle memory. Speech and formatting models load only when needed and are released after a period of inactivity.
  • Less work during silence in live preview, and tighter limits on audio buffers.
  • History and meeting lists load in pages, and background panels do less work.

1.2.3

Added

  • Optional usage sharing through Google Analytics, to help us improve reliability and understand how Blurt is used. It is off by default and lives under Settings → Privacy & data.
  • What it shares when you turn it on: usage events, durations, word counts, processing time, app version and operating system, under a resettable installation ID. Your audio and the text of your transcripts stay on the device.
  • Turning it off removes the local identifier and stops future collection. Analytics already received are not erased automatically.

1.2.2

Added

  • Optional background noise reduction, on device like everything else.
  • Four HUD positions, with compact vertical layouts for the two side ones.

Changed

  • Silence detection is stricter, so fewer stretches of nothing come back as text.
  • The waveform tracks your voice level more closely while you speak.
  • Home was refreshed, text reads more clearly throughout, and HUD position is now picked visually rather than from a list.

Fixed

  • Settings and History are more reliable.
  • A meeting transcript that arrives late now shows up instead of being dropped.
  • Diagnostic logs carry less of what you dictated.

1.2.0

Added

  • Metal GPU acceleration. Whisper now runs on the Apple Silicon GPU with tuned threads; large models went from about two minutes to seconds.
  • Quantised Whisper builds that need far less memory than the full model.
  • Review and edit before inserting. An optional editable box after recording: fix the text, then insert with ⌘↩ or discard with esc.
  • Live dictation. Text streams to the HUD as you speak.
  • Hands-free mode. Tap the trigger once to start, again to stop.
  • Word replacements and smart match in Dictionary, plus custom vocabulary to bias recognition toward your terms.
  • History editing, click-to-copy transcripts, and export through a Save dialog.

Changed

  • Plain-language model names in the picker instead of Base, Small and Turbo.
  • New Flowwave app icon, regenerated at every platform size.
  • The 500 MB model was removed, too close to the 574 MB one to justify keeping.

Fixed

  • The menu-bar icon is now a template image, so it renders as the wave glyph and recolours for light and dark menu bars instead of showing a solid white square.
  • Mode toggles apply immediately. Hands-free, live and review no longer need Save & Apply.
  • Toggle switches show their on and off state; the checked-state styling had only been applied to one of them.
  • The History list clamps to three lines with show more and less, and short entries stay unclamped.
  • The dashboard refreshes after each dictation, not only History.
  • The in-app Record button honours live mode.
  • The installer restores the executable bit and retries the launch, fixing Launch Services error -10810.

Try it for fourteen days

No card, no account, no email. Download and hold a key.

Download for Macv1.2.10 · Apple Silicon Mac, macOS 14 or later · Oct 14, 2026
14-day free trialNo card, no account · v1.2.10
Download for Mac