169 lines
9.2 KiB
Go
169 lines
9.2 KiB
Go
package config
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
)
|
|
|
|
func SaveDefaultConfig() error {
|
|
configPath, err := GetConfigPath()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
file, err := os.Create(configPath)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to create config file: %w", err)
|
|
}
|
|
defer file.Close()
|
|
|
|
configContent := `# Hyprvoice Configuration
|
|
# This file is automatically generated with defaults.
|
|
# Edit values as needed - changes are applied immediately without daemon restart.
|
|
#
|
|
# MIGRATION NOTE: If upgrading from an older version, your transcription.api_key
|
|
# will be automatically migrated to the new [providers.X] format. Run 'hyprvoice configure'
|
|
# to update your config file structure.
|
|
|
|
# Keywords help both transcription and LLM understand domain-specific terms
|
|
# Add names, technical terms, or brand names that might be misheard
|
|
keywords = []
|
|
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
# Provider API Keys
|
|
# Configure API keys for each provider you want to use.
|
|
# Keys can also be set via environment variables: OPENAI_API_KEY, GROQ_API_KEY, etc.
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
|
|
[providers.openai]
|
|
api_key = "" # OpenAI API key (or set OPENAI_API_KEY env var)
|
|
|
|
[providers.groq]
|
|
api_key = "" # Groq API key (or set GROQ_API_KEY env var)
|
|
|
|
# Uncomment to configure additional providers:
|
|
# [providers.mistral]
|
|
# api_key = "" # Mistral API key (or set MISTRAL_API_KEY env var)
|
|
# [providers.elevenlabs]
|
|
# api_key = "" # ElevenLabs API key (or set ELEVENLABS_API_KEY env var)
|
|
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
# Audio Recording
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
|
|
[recording]
|
|
sample_rate = 16000 # Audio sample rate in Hz (16000 recommended for speech)
|
|
channels = 1 # Number of audio channels (1 = mono, 2 = stereo)
|
|
format = "s16" # Audio format (s16 = 16-bit signed integers)
|
|
buffer_size = 8192 # Internal buffer size in bytes (larger = less CPU, more latency)
|
|
device = "" # PipeWire audio device (empty = use default microphone)
|
|
channel_buffer_size = 30 # Audio frame buffer size (frames to buffer)
|
|
timeout = "5m" # Maximum recording duration (e.g., "30s", "2m", "5m")
|
|
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
# Speech Transcription
|
|
# Converts audio to text using speech-to-text APIs
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
|
|
[transcription]
|
|
provider = "openai" # "openai", "groq-transcription", "groq-translation", "mistral-transcription", "elevenlabs"
|
|
language = "" # Language code (empty = auto-detect, "en", "it", "es", "fr", etc.)
|
|
model = "whisper-1" # Model: OpenAI="whisper-1", Groq="whisper-large-v3", Mistral="voxtral-mini-latest", ElevenLabs="scribe_v1"
|
|
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
# LLM Post-Processing (Recommended)
|
|
# Cleans up transcribed text: removes stutters, adds punctuation, fixes grammar
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
|
|
[llm]
|
|
enabled = true # Enable LLM post-processing (highly recommended)
|
|
provider = "openai" # "openai" or "groq" (must have API key configured above)
|
|
model = "gpt-4o-mini" # OpenAI: "gpt-4o-mini", Groq: "llama-3.3-70b-versatile"
|
|
|
|
[llm.post_processing]
|
|
remove_stutters = true # Remove "um", "uh", repeated words
|
|
add_punctuation = true # Add proper punctuation
|
|
fix_grammar = true # Fix grammatical errors
|
|
remove_filler_words = true # Remove "like", "you know", "basically"
|
|
|
|
[llm.custom_prompt]
|
|
enabled = false # Enable custom instructions for LLM
|
|
prompt = "" # Additional instructions (e.g., "Format as bullet points")
|
|
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
# Text Injection
|
|
# How transcribed text is inserted into applications
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
|
|
[injection]
|
|
backends = ["ydotool", "wtype", "clipboard"] # Ordered fallback chain (tries each until one succeeds)
|
|
ydotool_timeout = "5s" # Timeout for ydotool commands
|
|
wtype_timeout = "5s" # Timeout for wtype commands
|
|
clipboard_timeout = "3s" # Timeout for clipboard operations
|
|
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
# Desktop Notifications
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
|
|
[notifications]
|
|
enabled = true # Enable desktop notifications
|
|
type = "desktop" # "desktop", "log", or "none"
|
|
|
|
# Custom notification messages (optional - defaults shown below)
|
|
# Uncomment and modify to customize notification text
|
|
# [notifications.messages]
|
|
# [notifications.messages.recording_started]
|
|
# title = "Hyprvoice"
|
|
# body = "Recording Started"
|
|
# [notifications.messages.transcribing]
|
|
# title = "Hyprvoice"
|
|
# body = "Recording Ended... Transcribing"
|
|
# [notifications.messages.llm_processing]
|
|
# title = "Hyprvoice"
|
|
# body = "Processing..."
|
|
# [notifications.messages.config_reloaded]
|
|
# title = "Hyprvoice"
|
|
# body = "Config Reloaded"
|
|
# [notifications.messages.operation_cancelled]
|
|
# title = "Hyprvoice"
|
|
# body = "Operation Cancelled"
|
|
# [notifications.messages.recording_aborted]
|
|
# body = "Recording Aborted"
|
|
# [notifications.messages.injection_aborted]
|
|
# body = "Injection Aborted"
|
|
#
|
|
# Emoji-only example (for minimal pill-style notifications):
|
|
# [notifications.messages.recording_started]
|
|
# title = ""
|
|
# body = "..."
|
|
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
# Reference: Provider Details
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
#
|
|
# Transcription providers:
|
|
# - "openai": OpenAI Whisper API (cloud-based, excellent accuracy)
|
|
# - "groq-transcription": Groq Whisper API (very fast, models: whisper-large-v3, whisper-large-v3-turbo)
|
|
# - "groq-translation": Groq translation to English (always outputs English text, model: whisper-large-v3)
|
|
# - "mistral-transcription": Mistral Voxtral API (excellent for European languages, model: voxtral-mini-latest)
|
|
# - "elevenlabs": ElevenLabs Scribe API (99 languages, models: scribe_v1, scribe_v2)
|
|
#
|
|
# LLM providers (for post-processing):
|
|
# - "openai": GPT models (gpt-4o-mini recommended for cost/quality balance)
|
|
# - "groq": Fast inference (llama-3.3-70b-versatile recommended)
|
|
#
|
|
# Injection backends:
|
|
# - "ydotool": Uses ydotool (requires ydotoold daemon). Best for Chromium/Electron apps.
|
|
# - "wtype": Uses wtype for Wayland. May have issues with some Chromium apps.
|
|
# - "clipboard": Copies to clipboard only (most reliable, requires manual paste).
|
|
#
|
|
# Language codes: "" (auto-detect), "en", "it", "es", "fr", "de", "pt", etc.
|
|
`
|
|
|
|
if _, err := file.WriteString(configContent); err != nil {
|
|
return fmt.Errorf("failed to write config content: %w", err)
|
|
}
|
|
|
|
return nil
|
|
}
|