v0.4.0 — signed & distributable
plannedA signed installer with no SmartScreen warning, the updater repointed to AudioBud so automatic updates work again, and a self-contained install.
View milestone →Roadmap
Where AudioBud is headed.
Themes and status, not dates. Each milestone links to its issues on GitHub. Near-term versions carry firm issue lists; the later feature bets are directional, and v1.0.0 is a quality gate.
v0.5.0 — stability & reliability
plannedThe remaining inherited reliability bugs and a full accessibility pass across the settings, model picker, and dialogs.
View milestone →v0.6.0 — on-device AI cleanup
plannedOptional transcript cleanup with a local LLM — never the cloud — plus cheaper accuracy wins, the long-audio fix, and a real-time preview.
View milestone →v0.7.0 — interaction & personality
plannedVoice-driven editing commands, an in-app tutorial, and more of the frog mascot's personality.
View milestone →v1.0.0 — cross-platform & stable
plannedValidate the macOS and Linux builds, finish the remaining hardening, and complete the documentation.
View milestone →What has shipped.
Released builds, newest first. The full notes live in the changelog.
v0.3.4
shippedA dictation-quality release: spoken numbers come through as digits and symbols ($25, 10%, 3.5), a tray switcher flips between formatted and raw output without opening settings, and raw mode gained the groundwork to read spoken punctuation.
Release notes →v0.3.3
shippedA naming release: the tray tooltip, the command line, and the headers AudioBud sends to post-processing providers all name the app rather than the project it forked from.
Release notes →v0.3.2
shippedA translation release: the 19 languages AudioBud ships besides English now cover the whole interface, the app calls itself AudioBud in them rather than Handy, and the learned-words counter agrees with its count.
Release notes →v0.3.1
shippedA stability patch for the default setup: dictation now starts on Windows accounts with non-English names, history settings no longer delete unsaved recordings, pasting keeps what you had copied, and a stuck engine can no longer hang the window.
Release notes →v0.3.0
shippedOpt-in, on-device personalization: AudioBud learns the words you use most from your own dictation history and applies the ones you accept, with view, export, and reset controls.
Release notes →v0.2.0
shippedA self-contained installer with a portable build, the overlay placement grid, tray quick-toggles, and a dictionary that stops correcting words that were already right.
Release notes →v0.1.0
shippedThe first working local prototype, forked from Handy with the frog and swamp identity and a Windows-first default engine.
Release notes →Exploring, not scheduled: wake-word activation and local audio-file transcription are research bets with no milestone yet. They join the roadmap only once they prove out.
All issues