Skip to content

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 → AI Plugins, pick a dictation engine:

Engine Languages Download
Native Your OS’s built-in dictation (double-tap Fn on macOS) none
Parakeet v2 English ~630 MB
Parakeet v3 25 European languages ~640 MB

The Parakeet models are one-time downloads managed right in settings — install, and uninstall when you no longer need them.

  1. Place your cursor in a manuscript or note.
  2. Hold the push-to-talk shortcutMeta+Space by default (configurable in settings).
  3. Speak. A floating waveform shows that you’re being heard.
  4. Release the shortcut — your words appear at the cursor.

Dictation doesn’t just 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.