What works locally
Speech recognition, dictated text, personal dictionary and local history run on the desktop device. After the required language resources are present, day-to-day dictation does not need a cloud transcription service.
Offline speech to text
Dictovo turns speech into text on your computer. Your dictated audio and text stay on the device during transcription, while a small set of account and update functions still use the network.
Why Dictovo
Speech recognition, dictated text, personal dictionary and local history run on the desktop device. After the required language resources are present, day-to-day dictation does not need a cloud transcription service.
Initial language downloads, license validation, release metadata and optional anonymous telemetry can connect to Dictovo services. These functions are separate from dictated audio and text.
Offline should describe the speech-processing path, not pretend the whole product never connects. Dictovo documents both sides so teams can evaluate the real boundary.
Evaluate the fit
Install a published build, activate the license and download any language resources you need.
Keep the desktop app running and dictate into the active field. Important text should still be reviewed before it is sent or published.
Plans
Personal supports one active device. Pro adds desktop Meetings and a second active device. Team starts at two separate member licenses.
FAQ
No. Dictated speech and resulting text are processed on the supported desktop device.
Installation, activation, release checks and initial language resources can require a connection. The dictation processing itself is local.
No. Optional anonymous app telemetry can be disabled in Settings and must not contain dictated audio or text.
Dictovo publishes Mac and Windows builds. Check the public release feed for current versions and minimum operating systems.