Skip to content

2.0.3 — First-run setup, visible personas

Latest
Latest

Choose a tag to compare

View all tags
@PerIPan PerIPan released this 18 Aug 12:45
v2.0.3
177ed45
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

First-run setup

A four-pane sheet on first launch: permissions, dictation, voice, and connecting your coding agent. It replaces being dropped into the Settings window with a wall of JSON on top of it, and carries model-download progress the whole way through — including the ~1.5 GB speech model, which used to download with nothing on screen explaining the wait.

Skippable at every step, and reopenable any time from the menubar → Setup….

The agent pane detects which agents you actually have and lists those first. Previously first-run always showed Claude Code config regardless of what you run, because nothing was stored yet and Claude Code was the fallback. Codex users now also get told about hook trust in the app — Codex silently skips untrusted hooks, so without that step dictated turns are just quietly silent.

Personas are no longer a secret

Choosing a voice has always attached a national character to every spoken reply — French dry and faintly unimpressed, Hindi irrepressibly helpful, British dry and unflappable. It applied on every turn, it was derived from the voice id, and nothing in the app ever said so.

Now:

  • The voice picker names each language group's persona, so you can compare before choosing.
  • Settings → Agents → Persona lets you pick a different one, and spells out the one in force. It defaults to Automatic — the voice's own character — so nothing changes unless you change it.

Multilingual (Supertonic) voices get no persona automatically, so selecting one here is currently the only way to give them any character at all.

It lives with the agents rather than the voice because it instructs the model about the words it writes — it never reaches the synthesiser, so it has no effect on how the voice sounds. One persona applies to every connected agent; override per project with OW_TTS_PERSONA.

Also

  • Larger type throughout the windows. The dictation overlay is deliberately untouched.
  • OW_TTS_PERSONA for per-project overrides, alongside the existing OW_TTS_* variables.

Install

Download the DMG below, drag to Applications, and launch. If macOS quarantines it:

xattr -d com.apple.quarantine ~/Downloads/OpenWhisperer-2.0.3.dmg

This build is ad-hoc signed, so macOS will ask for Accessibility and Microphone permission again after replacing an existing install.

Assets 3
Loading