โš™๏ธ Configuration

Configuration

WinterMelon Scribe uses a .env file for configuration. Copy .env.example to .env and modify as needed:

cp .env.example .env

Transcription Service Configuration

Choose ONE transcription provider:

SiliconFlow (Recommended)

SILICONFLOW_API_KEY=your-api-key-here
# Optional: specify model
SILICONFLOW_MODEL=FunAudioLLM/SenseVoiceSmall

Groq Alternative

GROQ_API_KEY=your-groq-api-key-here
TRANSCRIPTION_PROVIDER=groq
# Optional: specify model
GROQ_MODEL=whisper-large-v3-turbo

LLM Enhancement Settings

Enable and configure AI text processing:

# Enable LLM processing
LLM_ENABLED=true

# OpenAI configuration
OPENAI_API_KEY=your-openai-api-key-here
OPENAI_MODEL=gpt-3.5-turbo

# Processing parameters
LLM_TEMPERATURE=0.7
LLM_MAX_TOKENS=1000

Custom Prompt Example

LLM_CUSTOM_PROMPT=Please optimize the expression of the following text:

Notification Settings

Configure system notifications:

# Enable notifications
NOTIFICATION_ENABLED=true

# Enable notification sounds
NOTIFICATION_SOUND_ENABLED=true

Complete Example

# .env file
# SiliconFlow (recommended)
SILICONFLOW_API_KEY=your-api-key-here

# Groq alternative
# GROQ_API_KEY=your-groq-api-key-here
# TRANSCRIPTION_PROVIDER=groq

# LLM enhancement
LLM_ENABLED=true
OPENAI_API_KEY=your-openai-api-key-here
OPENAI_MODEL=gpt-3.5-turbo

# Custom processing
LLM_CUSTOM_PROMPT=Please optimize the following text:

# Notifications
NOTIFICATION_ENABLED=true
NOTIFICATION_SOUND_ENABLED=true

# Debug mode (development only)
# DEBUG=true

API Key Management

SiliconFlow

Groq

OpenAI

Applying Changes

After modifying .env:

For Background Service (User Install)

./uninstall.sh && ./install.sh

For Direct Run (Developer Mode)

# Stop the current process
# Then restart
source .venv/bin/activate
python main.py

Environment Variables Reference

VariableRequiredDescription
SILICONFLOW_API_KEYYes (if using SiliconFlow)API key for SiliconFlow
GROQ_API_KEYYes (if using Groq)API key for Groq
TRANSCRIPTION_PROVIDEROptionalsiliconflow (default) or groq
OPENAI_API_KEYYes (if using LLM)API key for OpenAI
LLM_ENABLEDOptionaltrue or false (default)
OPENAI_MODELOptionalgpt-3.5-turbo, gpt-4, etc.
LLM_TEMPERATUREOptional0.0-1.0 (default: 0.7)
LLM_MAX_TOKENSOptionalMaximum output tokens
NOTIFICATION_ENABLEDOptionaltrue (default) or false
DEBUGOptionaltrue or false (development only)