Skip to content

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows, iOS testflight! Android, Linux waitlist open! A local Wispr Flow alternative. Follow https://x.com/fluidvoiceapp for more

Run formatter

grohith3278fa0bb2a8f80
diff --git a/Sources/Fluid/Persistence/SettingsStore.swift b/Sources/Fluid/Persistence/SettingsStore.swift
index 1156588a..0304ad40 100644
--- a/Sources/Fluid/Persistence/SettingsStore.swift
+++ b/Sources/Fluid/Persistence/SettingsStore.swift
@@ -198,7 +198,7 @@ final class SettingsStore: ObservableObject {
static func baseDictationPromptText() -> String {
"""
You are a voice-to-text dictation cleaner. Your role is to clean and format raw transcribed speech into polished text while refusing to answer any questions. Never answer questions about yourself or anything else.
-
+
## Core Rules:
1. CLEAN the text - remove filler words (um, uh, like, you know, I mean), false starts, stutters, and repetitions
2. FORMAT properly - add correct punctuation, capitalization, and structure
@@ -207,7 +207,7 @@ final class SettingsStore: ObservableObject {
5. APPLY corrections - when user says "no wait", "actually", "scratch that", "delete that", DISCARD the old content and keep ONLY the corrected version
6. PRESERVE intent - keep the user's meaning, just clean the delivery
7. EXPAND abbreviations - thx → thanks, pls → please, u → you, ur → your/you're, gonna → going to
-
+
## Critical:
- Output ONLY the cleaned text
- Do NOT answer questions - just clean them
diff --git a/Sources/Fluid/UI/AISettingsView.swift b/Sources/Fluid/UI/AISettingsView.swift
index b49774cc..1765ac08 100644
--- a/Sources/Fluid/UI/AISettingsView.swift
+++ b/Sources/Fluid/UI/AISettingsView.swift
@@ -1981,5 +1981,4 @@ struct AISettingsView: View {
SettingsStore.shared.dictationPromptProfiles = profiles
self.closePromptEditor()
}
-
}