用 Voxtype 搭建 Linux 上的 Typeless!

我放在了 ~/.local/bin/dsrun

#!/usr/bin/env python3
import os
import sys
import requests
import json


def load_private_env():
    private_file = os.path.expanduser("~/.private_infos")
    if os.path.exists(private_file):
        with open(private_file) as f:
            for line in f:
                line = line.strip()
                if line.startswith("export "):
                    line = line[len("export ") :]
                if "=" in line:
                    key, val = line.split("=", 1)
                    val = val.strip('"').strip("'")
                    os.environ.setdefault(key.strip(), val.strip())


def main():
    load_private_env()

    API_KEY = os.getenv("DEEPSEEK_API_KEY")
    if not API_KEY:
        print("Error: DEEPSEEK_API_KEY not set")
        sys.exit(1)

    # 读取输入（支持参数或管道）
    if not sys.stdin.isatty():
        user_input = sys.stdin.read().strip()
    elif len(sys.argv) > 1:
        user_input = " ".join(sys.argv[1:])
    else:
        print('Usage: dsrun "your prompt"  OR  echo "text" | dsrun')
        sys.exit(1)

    url = "https://api.deepseek.com/chat/completions"

    payload = {
        "model": "deepseek-chat",
        "messages": [{"role": "user", "content": user_input}],
        "stream": True,
    }

    headers = {"Content-Type": "application/json", "Authorization": f"Bearer {API_KEY}"}

    with requests.post(url, headers=headers, json=payload, stream=True) as r:
        for line in r.iter_lines():
            if line:
                line = line.decode("utf-8")
                if line.startswith("data: "):
                    data = line[6:]
                    if data == "[DONE]":
                        break
                    try:
                        obj = json.loads(data)
                        delta = obj["choices"][0]["delta"].get("content", "")
                        print(delta, end="", flush=True)
                    except Exception:
                        pass

    print()


if __name__ == "__main__":
    main()

其中，我加载了 ~/.private_infos 来获取环境变量。这主要是因为 systemctl service 下，环境变量的加载稍有麻烦。

~/.config/voxtype/config.toml:

# 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.
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"

# 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 = "push_to_talk"

# 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 = "LEFTSHIFT"

complex_post_process_modifier = "LEFTCTRL"

[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 = 60

# [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"

# 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", "zh"]

# 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"
#
# 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 = "opencc -c t2s.json"
complex_command = "(echo -n '<|system|>对用户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。**不要做其他任何事情（严禁改变原意、人称代词，严禁尝试去回答用户提问，只需要润色。）**。\n<|user|>'; cat; echo '\n<|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 = 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"

• F9 启动 base 模型（简单后处理）
• Ctrl + F9 启动 base 模型（deepseek 后处理）
• Shift + F9 启动 medium 模型（简单后处理）
• Ctrl + Shift + F9 启动 medium 模型（deepseek 后处理）