.env.sample

# Conditional API Usage:
# Depending on the value of MODEL_PROVIDER, the corresponding service will be used when run.
# You can mix and match; use local Ollama with OpenAI speech or use OpenAI model with local XTTS, etc.

# Model Provider: openai or ollama
MODEL_PROVIDER=ollama

# Character Configuration: SEE CHARACTERS FOLDER FOR ALL OF THEM
# Character to use - Options: samantha, wizard, pirate, valleygirl, newscaster1920s, alien_scientist, cyberpunk, detective,                  
# mouse, conandoyle, shakespeare, einstein, nerd, joker, terminator, insult, vampire, ghost, conspiracy, clumsyhero, dog .......
CHARACTER_NAME=insult

# Text-to-Speech (TTS) Configuration:
# TTS Provider - Options: xtts (local uses the custom character .wav) or openai (uses OpenAI TTS voice) or elevenlabs
TTS_PROVIDER=elevenlabs

# OpenAI TTS Voice - Used when TTS_PROVIDER is set to openai above
# Voice options: alloy, echo, fable, onyx, nova, shimmer
OPENAI_TTS_VOICE=onyx

# ElevenLabs Configuration:
ELEVENLABS_API_KEY=49b111111111
# Default voice ID
ELEVENLABS_TTS_VOICE=VgPpppppppp

# XTTS Configuration:
# The voice speed for XTTS only (1.0 - 1.5, default is 1.1)
XTTS_SPEED=1.2

# OpenAI Configuration:
# OpenAI API Key for models and speech (replace with your actual API key)
OPENAI_API_KEY=sk-proj-1111111
# Models to use - OPTIONAL: For screen analysis, if MODEL_PROVIDER is ollama, llava will be used by default.
# Ensure you have llava downloaded with Ollama. If OpenAI is used, gpt-4o works well.
OPENAI_MODEL=gpt-4o

# Endpoints:
# Set these below and no need to change often
OPENAI_BASE_URL=https://api.openai.com/v1/chat/completions
OPENAI_TTS_URL=https://api.openai.com/v1/audio/speech
OLLAMA_BASE_URL=http://localhost:11434

# Models Configuration:
# Models to use - llama3 works well for local usage.
OLLAMA_MODEL=llama3

# NOTES:
# List of trigger phrases to have the model view your desktop (desktop, browser, images, etc.).
# It will describe what it sees, and you can ask questions about it:
# "what's on my screen", "take a screenshot", "show me my screen", "analyze my screen", 
# "what do you see on my screen", "screen capture", "screenshot"