[Requests and ideas] Voice dictation work fine for english, but as always it fails to capture some...

**Mood:** 😊
**Category:** Requests and ideas

Voice dictation work fine for english, but as always it fails to capture some technical terms, filenames and other acronyms we use regularly. One simple fix for that that other dictation tools already use would be to allow to add a simple dictionary of replacements, using either strings patterns or regex for advanced users, for example:

"package dot JSON" => `package.json`
"uh" => "" # remove filler words

Bonus points if that dictionary could be a simple text file, so it's easy to share and copy/paste.

---
| Field | Value |
| --- | --- |
| App version | 0.2.31 |
| OS | macOS 15.7.7 |
| Theme | Selene Selenized |
| Path | /chat |
| Tenure | Week 4 |

The issue does not name any files, tests, or entry points. Start by locating the app's voice-dictation flow and decide how replacement strings, regex patterns, and an optional shareable text file should be represented; done means the requested replacements work reliably for dictation output.

Rédigé par le modèle d'indexation à partir du texte de l'issue.