Skip to content

OpenWhisperer 1.5.1 — Auto-focus any app, Response mode

Latest
Latest

Choose a tag to compare

View all tags
@PerIPan PerIPan released this 26 Jun 08:40
v1.5.1
752ea9b
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

What's New in 1.5.1

  • Auto-focus any installed app — the Automation dropdown now offers a searchable list of every app installed on your Mac (Word, WhatsApp, Slack, …), alongside the curated dev/terminal favorites and a Custom entry. Pin dictation to whichever app you like, and search it by name.
  • Snappier menu — fixed a 3–4 second freeze when opening the menubar popover. A synchronous "launch at login" status check (an XPC call to launchservicesd) was blocking the main thread on every open; it now runs off-main.
  • Response mode — a new Response control in Voice Settings (beside Style) chooses when replies are spoken: when Voice (dictated turns only — the default, unchanged), when Text (typed turns only), or Always. Per-project override via OW_TTS_RESPONSE in .claude/settings.local.json.
  • Automation polish — "with return" is grouped under auto-focus, and the behavior hint now reflects your exact auto-focus / with-return / auto-submit combination.
  • In-app help — a hover ⓘ on every section explains what it does, and the Hook setup instructions are corrected to document both hooks (Stop + UserPromptSubmit).
  • Menu tidy — the auto-focus card is now App Focus Automation, the platform/setup card is Setup TTS for (with Volume tucked inside), and all section titles share one consistent weight.

The default behavior is unchanged: dictation types into the focused app, and only voice-dictated turns are spoken unless you opt into a different Response mode.

Install

Download OpenWhisperer-1.5.1.dmg below and drag it to Applications. The app isn't signed with a paid Apple Developer certificate, so allow it to run:

xattr -cr /Applications/OpenWhisperer.app

On first launch macOS asks for Microphone, Accessibility, and Speech Recognition permissions. First run also downloads the models (~1.7 GB) and compiles them for the Neural Engine (~1–2 min, one-time); every launch after is instant.

Assets 3
Loading