84e435f916
Adds /settings (served by the bridge) to change the LLM model (from installed Ollama models), Whisper model, TTS engine + MeloTTS speed, output language, agentic max-turns, thinking mode, and free-form LLM instructions — live, with a 'apply' that restarts the bridge + TTS worker. Settings persist to the runtime config JSON; engine reads output_language + llm_instructions and the TTS worker reads melo_speed from it. Bridge port publishable for access.
197 lines
10 KiB
Plaintext
197 lines
10 KiB
Plaintext
# ============================================================================
|
|
# Javis Bot — environment configuration
|
|
# Copy to `.env` and fill in. Never commit your real `.env`.
|
|
# ============================================================================
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Discord bot (normal bot account) — voice I/O + slash commands
|
|
# ---------------------------------------------------------------------------
|
|
# OPTIONAL — leave BLANK to run in userbot/selfbot mode (a single user account
|
|
# does voice + broadcast; see DISCORD_SELFBOT_TOKEN below). When this is empty
|
|
# and a selfbot token is present, the app runs as a userbot automatically.
|
|
# Only fill this in if you specifically want the legacy normal-bot path.
|
|
# From https://discord.com/developers/applications → your app
|
|
DISCORD_BOT_TOKEN=
|
|
DISCORD_APP_ID=
|
|
# The (single) server this bot serves. Guild-scoped commands appear instantly.
|
|
DISCORD_GUILD_ID=
|
|
# Voice channel used by the stream-test scripts (bot/scripts/stream-test).
|
|
DISCORD_VOICE_CHANNEL_ID=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Brain bridge (Python service in bridge/) — STT + reply engine + TTS
|
|
# ---------------------------------------------------------------------------
|
|
BRIDGE_URL=http://127.0.0.1:8765
|
|
BRIDGE_HOST=127.0.0.1
|
|
BRIDGE_PORT=8765
|
|
JARVIS_BRAIN_ENABLED=1
|
|
JARVIS_TTS_ENABLED=1
|
|
# faster-whisper device/compute. GPU by default (RTX 5050 / sm_120, verified).
|
|
# Falls back to CPU automatically if no GPU is passed to the container.
|
|
WHISPER_DEVICE=cuda
|
|
WHISPER_COMPUTE_TYPE=float16
|
|
# Optional explicit Piper voice model (.onnx). If empty, the jarvis default is used.
|
|
TTS_PIPER_MODEL_PATH=
|
|
# TTS engine: "melo" (default) uses the MeloTTS Korean voice served by the warm
|
|
# melo-worker (Korean speaker, speed 1.5). Set to "piper" to use Piper directly.
|
|
TTS_ENGINE=melo
|
|
# Melo-only by default: if MeloTTS synthesis fails the bridge returns no audio
|
|
# rather than speaking Korean through the English Piper voice (which mangles it).
|
|
# Set to 1 only if you explicitly want the Piper fallback.
|
|
MELO_FALLBACK_PIPER=0
|
|
# Where the bridge reaches the in-container MeloTTS worker, and how long it
|
|
# waits for a synthesis. Speaking rate is set on the worker via MELO_SPEED.
|
|
MELO_WORKER_URL=http://127.0.0.1:8770
|
|
MELO_TIMEOUT=30
|
|
MELO_SPEED=1.5
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Jarvis brain (Ollama-backed). In Docker these populate the rendered
|
|
# config (docker/jarvis-config.template.json). See src/jarvis/config.py.
|
|
# ---------------------------------------------------------------------------
|
|
# In docker-compose this is overridden to http://ollama:11434 automatically.
|
|
OLLAMA_BASE_URL=http://127.0.0.1:11434
|
|
# qwen2.5:3b — small non-reasoning instruct model. ~2.4GB, runs 100% on the GPU
|
|
# (the 8B offloads ~8% to CPU), warm voice turns ~2-4s vs ~5-7s on 8B. Clean
|
|
# Korean on factual/tool replies; can occasionally leak a trailing CJK phrase on
|
|
# free-form chit-chat. Swap back to qwen3:8b for the strongest tool-calling.
|
|
OLLAMA_CHAT_MODEL=qwen2.5:3b
|
|
# Model for the auxiliary small-model calls: intent judge, tool router, weather
|
|
# place extraction, query decomposition. BLANK (default) reuses OLLAMA_CHAT_MODEL
|
|
# so the stack runs on one already-warm model. The code's built-in default
|
|
# (gemma4:e2b) is NOT pulled by this stack, so leaving this unset previously made
|
|
# every router/extractor call silently fail. Only set this if you also pull the
|
|
# model into Ollama.
|
|
OLLAMA_INTENT_MODEL=
|
|
OLLAMA_EMBED_MODEL=nomic-embed-text
|
|
WHISPER_MODEL=small
|
|
|
|
# Lock every reply to one language, e.g. OUTPUT_LANGUAGE=Korean. Leave BLANK to
|
|
# keep the default behaviour of replying in whatever language the user wrote in.
|
|
# A fixed value also suppresses stray characters from other scripts (e.g. the
|
|
# occasional trailing CJK fragment small models leak on free-form chat).
|
|
OUTPUT_LANGUAGE=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Docker desktop (VNC) — used only by the container image
|
|
# ---------------------------------------------------------------------------
|
|
# VNC viewer password (max 8 chars effective). Watch the screen at localhost:5901.
|
|
# Also used by the broadcast keepalive: TigerVNC only refreshes its framebuffer
|
|
# while a VNC client is attached, so the stream keeps a tiny client connected to
|
|
# avoid a choppy (~1.5 fps) capture. Must match the VNC server's password. If
|
|
# unset, the keepalive falls back to the obfuscated passwd file (VNC_PASSWD_FILE,
|
|
# default ~/.config/tigervnc/passwd).
|
|
VNC_PASSWORD=javis123
|
|
# VNC_PASSWD_FILE=/home/claude/.config/tigervnc/passwd
|
|
# Auto-opened page in the in-container Chrome.
|
|
CHROME_START_URL=about:blank
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Screen-share + browser mode.
|
|
# true = the bot may go Live (screen-share the VNC desktop) and drive the
|
|
# on-screen browser for real-time info (search / play / read screen).
|
|
# false = no screen share; voice only, real-time info via the Gemini API.
|
|
STREAM_BROWSER=true
|
|
# Gemini auth for real-time info when STREAM_BROWSER=false.
|
|
# oauth = use the Gemini CLI with a Google-account login (no API key).
|
|
# Install once: npm i -g @google/gemini-cli ; then run `gemini` and
|
|
# "Sign in with Google". Uses the CLI's built-in web-search grounding.
|
|
# apikey = legacy REST path; needs GEMINI_API_KEY below
|
|
# (get one at https://aistudio.google.com/app/apikey).
|
|
GEMINI_AUTH=oauth
|
|
GEMINI_API_KEY=
|
|
GEMINI_MODEL=gemini-2.0-flash
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# VNC screen broadcast
|
|
# selfbot = real live "Go Live" stream (needs a USER/burner token; ToS risk)
|
|
# novnc = share a noVNC browser link (safe, real-time, not native)
|
|
# screenshot = periodic screenshots to the channel (safe, low fps)
|
|
# none = disabled
|
|
# ---------------------------------------------------------------------------
|
|
STREAM_BACKEND=selfbot
|
|
|
|
# The VNC desktop runs on X display :1 (see docs/vnc-xfce-setup.md)
|
|
VNC_DISPLAY=:1
|
|
VNC_RESOLUTION=1920x1080
|
|
# 1080p60 broadcast. 8 Mbps suits 60fps (YouTube-style 1080p60 sits ~8-12 Mbps);
|
|
# drop to 30/4000 for a lighter stream. Max bitrate is 1.5x this value.
|
|
VNC_FRAMERATE=60
|
|
VNC_BITRATE_KBPS=8000
|
|
|
|
# --- selfbot backend ---
|
|
# A THROWAWAY/burner Discord user account token. NEVER your main account.
|
|
# Using a selfbot violates Discord ToS and can get the account banned.
|
|
DISCORD_SELFBOT_TOKEN=
|
|
# Dedicated burner account for the Go-Live BROADCAST, separate from the
|
|
# conversation account above. REQUIRED in userbot mode for the broadcast to
|
|
# work: Discord allows only one voice presence per account, so the conversation
|
|
# and the broadcast cannot share one account (the broadcaster's voice connection
|
|
# never connects). Leave empty in normal-bot mode (the conversation runs on the
|
|
# bot account, so the selfbot account is already broadcast-only). Both burner
|
|
# accounts must be in the server. Use a second throwaway account, never a main.
|
|
DISCORD_STREAM_TOKEN=
|
|
# Hardware (NVENC) encode for the stream. 1 = use the GPU (recommended for
|
|
# 1080p60), 0 = software x264. Requires an NVIDIA GPU + ffmpeg built with nvenc.
|
|
STREAM_HW=1
|
|
# Capture desktop audio into the broadcast so the stream has sound. 1 = on,
|
|
# 0 = mute. Pulls the PipeWire/Pulse monitor of the default sink; override the
|
|
# source with STREAM_AUDIO_SOURCE (e.g. a specific "<sink>.monitor").
|
|
STREAM_AUDIO=1
|
|
STREAM_AUDIO_SOURCE=@DEFAULT_MONITOR@
|
|
|
|
# --- novnc backend ---
|
|
# e.g. http://192.168.10.9:6080/vnc.html (websockify --web=/usr/share/novnc 6080 localhost:5901)
|
|
NOVNC_URL=
|
|
|
|
# --- screenshot backend ---
|
|
SCREENSHOT_INTERVAL_SEC=5
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Voice behaviour
|
|
# ---------------------------------------------------------------------------
|
|
# Silence (ms) that marks the end of an utterance before sending to the brain.
|
|
VOICE_SILENCE_MS=800
|
|
|
|
# ===========================================================================
|
|
# Split deployment & cross-platform (Ubuntu + Windows 11)
|
|
# ===========================================================================
|
|
# JARVIS_ROLE selects what this machine runs (see docker/run-if-role.sh):
|
|
# full (default) everything in one container
|
|
# browser ONLY the desktop + Chrome + control-server (driven over the LAN)
|
|
# bot ONLY the bot + bridge + TTS (drives a REMOTE browser)
|
|
JARVIS_ROLE=full
|
|
|
|
# --- GPU per OS: pick the matching compose override via COMPOSE_FILE ---
|
|
# Ubuntu (nvidia-container-toolkit / CDI):
|
|
# COMPOSE_FILE=docker-compose.yml:docker-compose.gpu-linux.yml
|
|
# Windows 11 (Docker Desktop + WSL2 + NVIDIA):
|
|
# COMPOSE_FILE=docker-compose.yml:docker-compose.gpu-windows.yml
|
|
# Browser-only host (no GPU needed): leave COMPOSE_FILE unset (base only).
|
|
COMPOSE_FILE=docker-compose.yml:docker-compose.gpu-linux.yml
|
|
|
|
# --- Browser HOST (JARVIS_ROLE=browser) — e.g. this LAN machine ---
|
|
# Expose Chrome control to the internal network (no auth, internal only):
|
|
# CDP_BIND=0.0.0.0
|
|
# BROWSER_CONTROL_BIND=0.0.0.0
|
|
# CDP_PUBLISH_BIND=0.0.0.0
|
|
# Defaults are loopback-only.
|
|
|
|
# --- BOT host (JARVIS_ROLE=bot) — e.g. your PC driving the remote browser ---
|
|
# Point the controlBrowser tool at the browser host's control-server:
|
|
# BROWSER_CONTROL_URL=http://192.168.10.9:8777
|
|
# (Leave BROWSER_CONTROL_URL empty on full/browser layouts.)
|
|
|
|
# --- Models (tune per machine) ---
|
|
# OLLAMA_CHAT_MODEL=qwen2.5:7b # quality (needs ~5GB VRAM + whisper small)
|
|
# OLLAMA_CHAT_MODEL=qwen2.5:3b # speed (fits easily, faster on 8GB GPUs)
|
|
# WHISPER_MODEL=small # small frees VRAM for a bigger LLM; medium=more accurate
|
|
# MELO_DEVICE=cuda # cpu if no GPU on the bot host
|
|
|
|
# --- Settings web UI (http://localhost:8765/settings on the bot host) ---
|
|
# To reach it, expose the bridge to the host loopback:
|
|
# BRIDGE_HOST=0.0.0.0
|
|
# SETTINGS_PUBLISH_BIND=127.0.0.1 # 0.0.0.0 to allow LAN access (no auth)
|
|
# Change models / STT / TTS speed / language / LLM instructions live; "적용"
|
|
# restarts the bridge + TTS worker so changes take effect.
|