Home/Docs/Dashboard & history

Dashboard & history

The dashboard is where the app keeps your history, your personalization, and every setting. Open it from the Dock icon, the menu bar, or ⌘⇧D.

Home

The headline number is time back — an estimate of how long the same text would have taken to type, computed at 40 words per minute against your actual dictated word count. Below it: total words, number of takes, and a running streak of days used.

The rest of the pane holds a “this week” chart of minutes returned per day, a breakdown of which apps you dictate into most (shown once you have used at least two), your three most recent takes, and — kept permanently — the very first thing you ever dictated.

About that estimate

40 wpm is a reasonable average typing speed, not a measurement of you. Treat the number as an order of magnitude, not a stopwatch.

History

Every take, with its timestamp, the app you dictated into, the text, and a word count. Each row has a Copy button.

History holds the most recent 500 entries and rolls over after that. It lives on your Mac in ~/Library/Application Support/OpenVoiceFlow/ and is never uploaded. Audio is not kept at all — only the resulting text.

To clear it: Settings ▸ Privacy ▸ Delete history…, which offers Delete, keep my first words or Delete everything. The first option exists because people tend to want the memento even when clearing the log.

The other panes

PaneWhat it is for
DictionaryWords it keeps getting wrong. Fix them once.
SnippetsSay the short thing, get the long thing.
StylesHow you sound, per app.
Know-MeA short profile that helps cleanup spell your world correctly.
SettingsPermissions, dictation, transcription, cleanup, privacy, and updates.

The waveform icon at the top right gives you the fast controls without opening the dashboard: pause listening for an hour, change the hotkey, change the cleanup backend, open permission settings, and check for updates.

Changing the speech model

Change your Whisper model from Dashboard ▸ Settings ▸ Transcription. That path loads the new model immediately. Selecting a model elsewhere may not take effect until the app is relaunched.

Documentation for OpenVoiceFlow 0.5.5 · last updated 2026-07-31. Something wrong or missing here? That is a bug — tell us at shimoverse@gmail.com.