Skip to content
ScriptoriumDocumentation
English
Download

Dictation (Speech-to-Text)

Dictate instead of type. Scriptorium’s dictation runs entirely on your device. Your voice is never sent to any server.

In  Settings ›  Plugins, pick a dictation engine:

EngineLanguagesDownload
Disablednonenone
Parakeet v3Multilingual~640 MB

The Parakeet model is a one-time download managed in settings. Install it, and uninstall it when you no longer need it.

Disabled is the default: no model, and Scriptorium’s dictation is off. Your operating system’s own dictation still works on top of Scriptorium, the way it does in any app (double-tap Fn on macOS). That is the OS talking, not a Scriptorium engine, and none of the smart transcription below applies to it.

  1. Place your cursor in a manuscript or note.
  2. Hold the push-to-talk shortcut: CtrlSpace by default (configurable in settings). Or pick  Dictation from the / menu.
  3. Speak. A floating waveform shows that you’re being heard.
  4. Release the shortcut. Your words appear at the cursor.

Dictation does more than transcribe. It cleans up as it goes:

  • Punctuation added automatically
  • Filler words (“um”, “uh”) removed
  • Pauses become paragraph breaks
  • Your vocabulary: add proper nouns per project (character names, invented places) so they’re recognized correctly
  • Custom replacements: define your own spoken phrases, e.g. saying “symbol open quote” inserts "

Audio is processed locally by the model on your machine. Nothing is uploaded, and dictation works fully offline once the model is installed.