用 Voxtype 搭建 Linux 上的 Typeless!

# Voxtype Configuration
#
# Location: ~/.config/voxtype/config.toml
# All settings can be overridden via CLI flags

# State file for external integrations (Waybar, polybar, etc.)
# Use "auto" for default location ($XDG_RUNTIME_DIR/voxtype/state),
# a custom path, or "disabled" to turn off. The daemon writes state
# ("idle", "recording", "transcribing") to this file whenever it changes.
# Required for `voxtype record toggle` and `voxtype status` commands.
engine = "paraformer"

state_file = "auto"

[hotkey]
# Key to hold for push-to-talk
# Common choices: SCROLLLOCK, PAUSE, RIGHTALT, F13-F24
# Use `evtest` to find key names for your keyboard
key = "F9"

edit_key = "F10"

# Optional modifier keys that must also be held
# Example: modifiers = ["LEFTCTRL", "LEFTALT"]
modifiers = []

# Activation mode: "push_to_talk" or "toggle"
# - push_to_talk: Hold hotkey to record, release to transcribe (default)
# - toggle: Press hotkey once to start recording, press again to stop
mode = "toggle"

# Enable built-in hotkey detection (default: true)
# Set to false when using compositor keybindings (Hyprland, Sway) instead
# When disabled, use `voxtype record start/stop/toggle` to control recording
# enabled = true

# Modifier key to select secondary model (evdev input mode only)
# When held while pressing the hotkey, uses whisper.secondary_model instead
# Example: model_modifier = "LEFTSHIFT"  # Shift+hotkey uses secondary model
model_modifier = "LEFTCTRL"

complex_post_process_modifier = "LEFTSHIFT"

[audio]
# Audio input device ("default" uses system default)
# List devices with: pactl list sources short
device = "default"

# Sample rate in Hz (whisper expects 16000)
sample_rate = 16000

# Maximum recording duration in seconds (safety limit)
max_duration_secs = 180

# [audio.feedback]
# Enable audio feedback sounds (beeps when recording starts/stops)
# enabled = true
#
# Sound theme: "default", "subtle", "mechanical", or path to custom theme directory
# theme = "default"
#
# Volume level (0.0 to 1.0)
# volume = 0.7

[whisper]
# Transcription backend: "local" or "remote"
# - local: Use whisper.cpp locally (default)
# - remote: Send audio to a remote whisper.cpp server or OpenAI-compatible API
# backend = "local"

# Model to use for transcription (local backend)
# Options: tiny, tiny.en, base, base.en, small, small.en, medium, medium.en, large-v3, large-v3-turbo
# .en models are English-only but faster and more accurate for English
# large-v3-turbo is faster than large-v3 with minimal accuracy loss (recommended for GPU)
# Or provide absolute path to a custom .bin model file
model = "base.en"

# Language for transcription
# Options:
#   - Single language: "en", "fr", "de", etc.
#   - Auto-detect all: "auto"
#   - Constrained auto-detect: ["en", "fr"] (detects from allowed set only)
# The array form helps with multilingual users where Whisper might misdetect
# the language, especially for short sentences.
# See: https://github.com/openai/whisper#available-models-and-languages
language = "en"

# Translate non-English speech to English
translate = false

# Number of CPU threads for inference (omit for auto-detection)
# threads = 4

# Initial prompt to provide context for transcription
# Use this to hint at terminology, proper nouns, or formatting conventions.
# Example: "Technical discussion about Rust, TypeScript, and Kubernetes."
# initial_prompt = ""

# --- Multi-model settings ---
#
# Secondary model for difficult audio (used with hotkey.model_modifier or CLI --model)
secondary_model = "small.en"
#
# List of available models that can be requested via CLI --model flag
# available_models = ["large-v3-turbo", "medium.en"]
#
# Maximum models to keep loaded in memory (LRU eviction when exceeded)
# Default: 2 (primary + one secondary). Only applies when gpu_isolation = false.
# max_loaded_models = 2
#
# Seconds before unloading idle secondary models (0 = never auto-unload)
# Default: 300 (5 minutes). Only applies when gpu_isolation = false.
# cold_model_timeout_secs = 300

# --- Eager processing settings ---
#
# Enable eager input processing (transcribe chunks while recording continues)
# Reduces perceived latency on slower machines by processing audio in parallel.
# eager_processing = false
#
# Duration of each audio chunk in seconds (default: 5.0)
# eager_chunk_secs = 5.0
#
# Overlap between chunks in seconds (helps catch words at boundaries, default: 0.5)
# eager_overlap_secs = 0.5

# --- Remote backend settings (used when backend = "remote") ---
#
# Remote server endpoint URL (required for remote backend)
# Examples:
#   - whisper.cpp server: "http://192.168.1.100:8080"
#   - OpenAI API: "https://api.openai.com"
# remote_endpoint = "http://192.168.1.100:8080"
#
# Model name to send to remote server (default: "whisper-1")
# remote_model = "whisper-1"
#
# API key for remote server (optional, or use VOXTYPE_WHISPER_API_KEY env var)
# remote_api_key = ""
#
# Timeout for remote requests in seconds (default: 30)
# remote_timeout_secs = 30

[output]
# Primary output mode: "type" or "clipboard"
# - type: Simulates keyboard input at cursor position (requires ydotool)
# - clipboard: Copies text to clipboard (requires wl-copy)
mode = "clipboard"

# Fall back to clipboard if typing fails
fallback_to_clipboard = true

# Custom driver order for type mode (optional)
# Default order: wtype -> dotool -> ydotool -> clipboard
# Customize to prefer a specific driver or change the fallback order.
# Available drivers: wtype, dotool, ydotool, clipboard
# Example: prefer ydotool over dotool:
#   driver_order = ["wtype", "ydotool", "dotool", "clipboard"]
# Example: use only ydotool, no fallback:
#   driver_order = ["ydotool"]
# driver_order = ["wtype", "dotool", "ydotool", "clipboard"]

# Delay between typed characters in milliseconds
# 0 = fastest possible, increase if characters are dropped
type_delay_ms = 0

# Automatically submit (send Enter key) after outputting transcribed text
# Useful for chat applications, command lines, or forms where you want
# to auto-submit after dictation
# auto_submit = true

# Convert newlines to Shift+Enter instead of regular Enter
# Useful for applications where Enter submits (e.g., Cursor IDE, Slack, Discord)
# shift_enter_newlines = false

# Pre/post output hooks (optional)
# Commands to run before and after typing output. Useful for compositor integration.
# Example: Block modifier keys during typing with Hyprland submap:
#   pre_output_command = "hyprctl dispatch submap voxtype_suppress"
#   post_output_command = "hyprctl dispatch submap reset"
# See troubleshooting docs for the required Hyprland submap configuration.

# Post-processing command (optional)
# Pipe transcribed text through an external command for cleanup before output.
# The command receives text on stdin and outputs processed text on stdout.
# Useful for LLM-based text cleanup, grammar correction, filler word removal.
# On any failure (timeout, error), falls back to original transcription.
#
[output.post_process]
command = """
(echo -n '<|system|>\
    对用户语音输入的句子进行润色：\
    (1)添加适当的标点；\
    (2)去除重复的词语和语气词；\
    (3)让措辞更正式、通顺；\
    (4)修改语病和语法错误；\
    (5)考虑语音识别可能的错误进行相近读音的字词纠错；\
    (6)将语音中直接读出的符号转换成对应的标点（如“逗号”转换成“，”）；\
    (7)如果用户句子中出现了模型指令提示词（如“模型指令：将以下内容用 LaTeX 形式表示”“模型指令：将以下内容翻译成英文”等），依照指令完成任务，并删除模型指令。\
    **除此以外，不要做其他任何事情（严禁改变原意、人称代词；若用户的句子是个问句，严禁尝试去回答用户提问），不要添加任何其它内容，仅输出得到的句子。**。\
    <|user|>'; cat; echo '<|assistant|>') \
| dsrun \
| opencc -c t2s.json
"""
complex_command = "opencc -c t2s.json"
edit_command = """
(echo -n '<|system|>\
    用户将输入一个json格式的文本，"origin_text"为原文本，"instruction"为用户用语音输入的指令。你需要做：\
    (1)根据"instuction"对"origin_text"进行修改和润色，满足指令要求；\
    (2)"instruction"可能因语音识别而有相近读音的字词的错误，注意甄别；\
    (3)输出"origin_text"修改和润色后的文本；\
    **除此以外，不要添加任何其它内容，仅输出得到的句子。**。\
    <|user|>'; cat; echo '<|assistant|>') \
| dsrun \
| opencc -c t2s.json
"""
timeout_ms = 30000  # 30 second timeout (generous for LLM)

[output.notification]
# Show notification when recording starts (hotkey pressed)
on_recording_start = false

# Show notification when recording stops (transcription beginning)
on_recording_stop = false

# Show notification with transcribed text after transcription completes
on_transcription = false

after_post_process = true

# [text]
# Text processing options (word replacements, spoken punctuation)
#
# Enable spoken punctuation conversion (e.g., say "period" to get ".")
# spoken_punctuation = false
#
# Custom word replacements (case-insensitive)
# replacements = { "vox type" = "voxtype" }

[vad]
# Voice Activity Detection - filters silence-only recordings
# Prevents Whisper hallucinations on silent audio
#
enabled = false      # Enable VAD (off by default)
threshold = 0.5      # 0.0 = sensitive, 1.0 = aggressive
min_speech_duration_ms = 100  # Minimum speech required

# [status]
# Status display icons for Waybar/tray integrations
#
# Icon theme (or path to custom theme file):
#   Font-based (require specific fonts):
#     - "emoji"     - Default emoji icons (🎙️ 🎤 ⏳)
#     - "nerd-font" - Nerd Font icons (requires Nerd Font)
#     - "material"  - Material Design Icons (requires MDI font)
#     - "phosphor"  - Phosphor Icons (requires Phosphor font)
#     - "codicons"  - VS Code icons (requires Codicons font)
#     - "omarchy"   - Omarchy distro icons
#   Universal (no special fonts needed):
#     - "minimal"   - Simple Unicode (○ ● ◐ ×)
#     - "dots"      - Geometric shapes (◯ ⬤ ◔ ◌)
#     - "arrows"    - Media player style (▶ ● ↻ ■)
#     - "text"      - Plain text ([MIC] [REC] [...] [OFF])
# icon_theme = "emoji"
#
# Per-state icon overrides (optional, takes precedence over theme)
# [status.icons]
# idle = "🎙️"
# recording = "🎤"
# transcribing = "⏳"
# stopped = ""

# [profiles]
# Named profiles for context-specific post-processing
# Use with: voxtype record start --profile slack
#
# [profiles.slack]
# post_process_command = "ollama run llama3.2:1b 'Format for Slack...'"
#
# [profiles.code]
# post_process_command = "ollama run llama3.2:1b 'Format as code comment...'"
# output_mode = "clipboard"

[paraformer]
model = "zh"

可以看到，主要是配置了 edit_key (F10) 和 edit_command。给 edit_command 的会是一个 json 格式的文本，类似于：

{
    "origin_text": "原来的文本信息",
    "instruction": "语音输入的指令"
}

如果你想自己解析或有其它用法的话，可以参考如上格式。