davidgasquez.com
🔧 Where my dotfiles lives in harmony and peace, most of the time
✨ Add voxtype dictation config
+2
-1
hypr/hyprland.conf
+2
-1
hypr/hyprland.conf
···
214
214
bind = $mainMod SHIFT, E, exec, uwsm app -- bemoji -n
215
215
216
216
# Whisper
217
-
bind = $mainMod SHIFT, O, exec, whispr
217
+
bind = $mainMod SHIFT, O, exec, voxtype record start
218
+
bindr = $mainMod SHIFT, O, exec, voxtype record stop
218
219
219
220
# Volume
220
221
bindel = ,XF86AudioRaiseVolume, exec, wpctl set-volume -l 1 @DEFAULT_AUDIO_SINK@ 2%+
+4
-1
hypr/setup.sh
+4
-1
hypr/setup.sh
···
6
6
WAYBAR_CONFIG_DIR="${HOME}/.config/waybar"
7
7
MAKO_CONFIG_DIR="${HOME}/.config/mako"
8
8
FUZZEL_CONFIG_DIR="${HOME}/.config/fuzzel"
9
+
VOXTYPE_CONFIG_DIR="${HOME}/.config/voxtype"
9
10
PICTURES_DIR="${HOME}/Pictures"
10
11
11
12
packages=(
···
30
31
wireplumber
31
32
wl-clip-persist
32
33
wl-clipboard
34
+
voxtype-bin
33
35
xdg-desktop-portal-gtk
34
36
xdg-desktop-portal-hyprland
35
37
xdg-utils
···
44
46
systemctl --user enable --now hyprpolkitagent.service
45
47
fi
46
48
47
-
mkdir -p "${HYPR_CONFIG_DIR}" "${WAYBAR_CONFIG_DIR}" "${MAKO_CONFIG_DIR}" "${FUZZEL_CONFIG_DIR}" "${PICTURES_DIR}"
49
+
mkdir -p "${HYPR_CONFIG_DIR}" "${WAYBAR_CONFIG_DIR}" "${MAKO_CONFIG_DIR}" "${FUZZEL_CONFIG_DIR}" "${VOXTYPE_CONFIG_DIR}" "${PICTURES_DIR}"
48
50
49
51
ln -sf "${DOTFILES}/hypr/wallpaper.png" "${PICTURES_DIR}/wallpaper.png"
50
52
ln -sf "${DOTFILES}/hypr/frappe.conf" "${HYPR_CONFIG_DIR}/frappe.conf"
···
58
60
ln -sf "${DOTFILES}/hypr/waybar/frappe.css" "${WAYBAR_CONFIG_DIR}/frappe.css"
59
61
ln -sf "${DOTFILES}/hypr/mako/config" "${MAKO_CONFIG_DIR}/config"
60
62
ln -sf "${DOTFILES}/hypr/fuzzel/fuzzel.ini" "${FUZZEL_CONFIG_DIR}/fuzzel.ini"
63
+
ln -sf "${DOTFILES}/hypr/voxtype/config.toml" "${VOXTYPE_CONFIG_DIR}/config.toml"
+169
hypr/voxtype/config.toml
+169
hypr/voxtype/config.toml
···
1
+
# Voxtype (https://github.com/peteonrails/voxtype) Configuration
2
+
3
+
# State file for external integrations (Waybar, polybar, etc.)
4
+
# Use "auto" for default location ($XDG_RUNTIME_DIR/voxtype/state),
5
+
# a custom path, or "disabled" to turn off. The daemon writes state
6
+
# ("idle", "recording", "transcribing") to this file whenever it changes.
7
+
# Required for `voxtype record toggle` and `voxtype status` commands.
8
+
state_file = "auto"
9
+
10
+
[hotkey]
11
+
# Key to hold for push-to-talk
12
+
# Common choices: SCROLLLOCK, PAUSE, RIGHTALT, F13-F24
13
+
# Use `evtest` to find key names for your keyboard
14
+
key = "SCROLLLOCK"
15
+
16
+
# Optional modifier keys that must also be held
17
+
# Example: modifiers = ["LEFTCTRL", "LEFTALT"]
18
+
modifiers = []
19
+
20
+
# Activation mode: "push_to_talk" or "toggle"
21
+
# - push_to_talk: Hold hotkey to record, release to transcribe (default)
22
+
# - toggle: Press hotkey once to start recording, press again to stop
23
+
# mode = "push_to_talk"
24
+
25
+
# Enable built-in hotkey detection (default: true)
26
+
# Set to false when using compositor keybindings (Hyprland, Sway) instead
27
+
# When disabled, use `voxtype record start/stop/toggle` to control recording
28
+
# enabled = true
29
+
30
+
[audio]
31
+
# Audio input device ("default" uses system default)
32
+
# List devices with: pactl list sources short
33
+
device = "default"
34
+
35
+
# Sample rate in Hz (whisper expects 16000)
36
+
sample_rate = 16000
37
+
38
+
# Maximum recording duration in seconds (safety limit)
39
+
max_duration_secs = 60
40
+
41
+
[audio.feedback]
42
+
# Enable audio feedback sounds (beeps when recording starts/stops)
43
+
enabled = true
44
+
#
45
+
# Sound theme: "default", "subtle", "mechanical", or path to custom theme directory
46
+
theme = "default"
47
+
#
48
+
# Volume level (0.0 to 1.0)
49
+
volume = 0.7
50
+
51
+
[whisper]
52
+
# Transcription backend: "local" or "remote"
53
+
# - local: Use whisper.cpp locally (default)
54
+
# - remote: Send audio to a remote whisper.cpp server or OpenAI-compatible API
55
+
# backend = "local"
56
+
57
+
# Model to use for transcription (local backend)
58
+
# Options: tiny, tiny.en, base, base.en, small, small.en, medium, medium.en, large-v3, large-v3-turbo
59
+
# .en models are English-only but faster and more accurate for English
60
+
# large-v3-turbo is faster than large-v3 with minimal accuracy loss (recommended for GPU)
61
+
# Or provide absolute path to a custom .bin model file
62
+
model = "large-v3-turbo"
63
+
64
+
# Language for transcription
65
+
# Use "en" for English, "auto" for auto-detection
66
+
# See: https://github.com/openai/whisper#available-models-and-languages
67
+
language = "en"
68
+
69
+
# Translate non-English speech to English
70
+
translate = false
71
+
72
+
# Number of CPU threads for inference (omit for auto-detection)
73
+
# threads = 4
74
+
75
+
# --- Remote backend settings (used when backend = "remote") ---
76
+
#
77
+
# Remote server endpoint URL (required for remote backend)
78
+
# Examples:
79
+
# - whisper.cpp server: "http://192.168.1.100:8080"
80
+
# - OpenAI API: "https://api.openai.com"
81
+
# remote_endpoint = "http://192.168.1.100:8080"
82
+
#
83
+
# Model name to send to remote server (default: "whisper-1")
84
+
# remote_model = "whisper-1"
85
+
#
86
+
# API key for remote server (optional, or use VOXTYPE_WHISPER_API_KEY env var)
87
+
# remote_api_key = ""
88
+
#
89
+
# Timeout for remote requests in seconds (default: 30)
90
+
# remote_timeout_secs = 30
91
+
92
+
[output]
93
+
# Primary output mode: "type" or "clipboard"
94
+
# - type: Simulates keyboard input at cursor position (requires ydotool)
95
+
# - clipboard: Copies text to clipboard (requires wl-copy)
96
+
mode = "clipboard"
97
+
98
+
# Fall back to clipboard if typing fails
99
+
fallback_to_clipboard = true
100
+
101
+
# Delay between typed characters in milliseconds
102
+
# 0 = fastest possible, increase if characters are dropped
103
+
type_delay_ms = 0
104
+
105
+
# Automatically submit (send Enter key) after outputting transcribed text
106
+
# Useful for chat applications, command lines, or forms where you want
107
+
# to auto-submit after dictation
108
+
# auto_submit = true
109
+
110
+
# Pre/post output hooks (optional)
111
+
# Commands to run before and after typing output. Useful for compositor integration.
112
+
# Example: Block modifier keys during typing with Hyprland submap:
113
+
# pre_output_command = "hyprctl dispatch submap voxtype_suppress"
114
+
# post_output_command = "hyprctl dispatch submap reset"
115
+
# See troubleshooting docs for the required Hyprland submap configuration.
116
+
117
+
# Post-processing command (optional)
118
+
# Pipe transcribed text through an external command for cleanup before output.
119
+
# The command receives text on stdin and outputs processed text on stdout.
120
+
# Useful for LLM-based text cleanup, grammar correction, filler word removal.
121
+
# On any failure (timeout, error), falls back to original transcription.
122
+
#
123
+
# [output.post_process]
124
+
# command = "ollama run llama3.2:1b 'Clean up this dictation. Fix grammar, remove filler words. Output only the cleaned text:'"
125
+
# timeout_ms = 30000 # 30 second timeout (generous for LLM)
126
+
127
+
[output.notification]
128
+
# Show notification when recording starts (hotkey pressed)
129
+
on_recording_start = false
130
+
131
+
# Show notification when recording stops (transcription beginning)
132
+
on_recording_stop = false
133
+
134
+
# Show notification with transcribed text after transcription completes
135
+
on_transcription = true
136
+
137
+
# [text]
138
+
# Text processing options (word replacements, spoken punctuation)
139
+
#
140
+
# Enable spoken punctuation conversion (e.g., say "period" to get ".")
141
+
# spoken_punctuation = false
142
+
#
143
+
# Custom word replacements (case-insensitive)
144
+
# replacements = { "vox type" = "voxtype" }
145
+
146
+
# [status]
147
+
# Status display icons for Waybar/tray integrations
148
+
#
149
+
# Icon theme (or path to custom theme file):
150
+
# Font-based (require specific fonts):
151
+
# - "emoji" - Default emoji icons (🎙️ 🎤 ⏳)
152
+
# - "nerd-font" - Nerd Font icons (requires Nerd Font)
153
+
# - "material" - Material Design Icons (requires MDI font)
154
+
# - "phosphor" - Phosphor Icons (requires Phosphor font)
155
+
# - "codicons" - VS Code icons (requires Codicons font)
156
+
# - "omarchy" - Omarchy distro icons
157
+
# Universal (no special fonts needed):
158
+
# - "minimal" - Simple Unicode (○ ● ◐ ×)
159
+
# - "dots" - Geometric shapes (◯ ⬤ ◔ ◌)
160
+
# - "arrows" - Media player style (▶ ● ↻ ■)
161
+
# - "text" - Plain text ([MIC] [REC] [...] [OFF])
162
+
# icon_theme = "emoji"
163
+
#
164
+
# Per-state icon overrides (optional, takes precedence over theme)
165
+
# [status.icons]
166
+
# idle = "🎙️"
167
+
# recording = "🎤"
168
+
# transcribing = "⏳"
169
+
# stopped = ""