Skip to content

OpenWhisperer 1.5.2 — Will-speak indicator, live overlay transcript, download progress

Choose a tag to compare

View all tags
@PerIPan PerIPan released this 07 Jul 07:28
· 275 commits to main since this release
v1.5.2
90038c5

What's New in 1.5.2

  • Will-speak indicator — the menu bar icon switches to a speaker (and the status pill reads Standby · will speak) whenever your next dictated turn's reply will be spoken, so a turn that silently won't speak (edited prompt, dictating twice into one buffer) no longer looks like a bug. It only arms when you dictate into a terminal or editor — dictating into WhatsApp or Safari won't light it.
  • Overlay transcription history fixed — the floating overlay's scrollable transcript pane had been empty since the pure-Swift port (it watched a log format only the old Python server wrote). It now shows every dictation as it happens, straight from the in-process pipeline.
  • First-run download progress — the menu now shows a live percentage while the ~1.5 GB speech model downloads, then a clear "compiling for the Neural Engine" message. If the load fails, a banner explains why with Retry and Copy Diagnostics buttons.
  • Copy Diagnostics — one click in Server & Logs copies a support-ready report (app/macOS versions, permission states, model/cache status, disk space, log tails) to the clipboard.
  • More reliable Codex replies — spoken replies for Codex CLI are now matched to your dictated turn by content (when the payload carries the turn's messages), so a parallel or typed turn can neither steal nor silence your dictated turn's reply.
  • Voice download hardening — alternative Kokoro voices (Bella, Michael, Siwis, …) reject bad server responses instead of caching an error page as a voice file.
  • Under the hood: CI now runs both test suites on every push, and the version number is single-sourced from Info.plist.

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-1.5.2.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