9fde3d31ba
## Performance Optimizations (3-10x faster responses) - STT beam_size reduced to 1 (3-5x faster transcription, minimal quality loss) - Smart query routing: Haiku (simple) → Sonnet (medium) → Opus (complex) - TTS cache for common phrases (27 pre-generated responses) - Sentence-level streaming TTS (start playing while generating) - Sample-based VAD timing (30x improvement in silence detection) ## TTS Engine Upgrade - Migrated from Chatterbox to Chatterbox-Turbo - Zero-shot voice cloning (no fine-tuning required) - Native paralinguistic tag support ([laugh], [sigh], [chuckle], etc.) - Emotion presets with temperature control - Improved marker conversion (*action*, (action), ~action~) ## Discord Bot Enhancements - Multi-agent support (Jarvis, Sage) - Improved voice receiving with discord-ext-voice-recv - Enhanced /join, /leave, /status commands - Per-agent personality configuration - Better audio sink/receiver implementation ## OpenClaw Integration - WebSocket support for Gateway communication - Query complexity routing (auto-select model) - Improved error handling and retries - Session management per Discord guild - Better latency tracking ## Pipeline Improvements - Sentence splitter for streaming optimization - Query router for intelligent model selection - Enhanced VAD receiver with sample-based timing - Improved audio buffering and format conversion - Better transcript management ## Documentation - Added QUICK_START.md (5-minute test guide) - Added OPTIMIZATION_SUMMARY.md (performance analysis) - Added DISCORD_OPTIMIZATION_TEST.md (testing guide) - Added USAGE_GUIDE.md (comprehensive usage) - Updated README.md with optimization details ## Utilities & Scripts - Added get_invite_link.py (Discord bot invite) - Added sync_commands.py, sync_to_guild.py (command sync) - Added test_gateway.py, test_stt.py (testing utilities) - Added openclaw_wrapper.py (wrapper script) - Removed create_mock_turn_model.py (no longer needed) ## Configuration Updates - STT model: medium → small (faster, acceptable quality) - TTS engine: chatterbox → coqui (Turbo integration) - Beam size: 5 → 1 (latency optimization) - Added emotion_exaggeration per agent - Updated .gitignore for project files Total: ~2105 insertions, ~462 deletions across 35 files Performance: ~5.5s total latency (down from 22-35s) Target: ~3.5s (achieved in simple queries with cache) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
78 lines
3.3 KiB
Text
78 lines
3.3 KiB
Text
# Jarvis Voice Bot - Environment Variables
|
|
# Copy this file to .env and fill in your actual values
|
|
|
|
# ============================================================================
|
|
# Discord Bot (REQUIRED)
|
|
# ============================================================================
|
|
# Get your bot token from: https://discord.com/developers/applications
|
|
# 1. Create application → Bot → Copy token
|
|
# 2. Enable Privileged Gateway Intents: Server Members, Message Content
|
|
DISCORD_BOT_TOKEN=your_discord_bot_token_here
|
|
|
|
# ============================================================================
|
|
# OpenClaw Gateway (REQUIRED)
|
|
# ============================================================================
|
|
# Your OpenClaw Gateway WebSocket on Synology NAS
|
|
# Format: ws://IP:PORT (default port is 18789)
|
|
OPENCLAW_BASE_URL=ws://192.168.50.9:18789
|
|
OPENCLAW_AUTH_TOKEN=your_openclaw_gateway_token
|
|
OPENCLAW_AGENT_ID=main # Agent ID for session keys (jarvis or main)
|
|
|
|
# ============================================================================
|
|
# FastAPI Server
|
|
# ============================================================================
|
|
SERVER_HOST=0.0.0.0
|
|
SERVER_PORT=8880
|
|
|
|
# ============================================================================
|
|
# Pipeline Configuration (OPTIONAL OVERRIDES)
|
|
# ============================================================================
|
|
# These override values from config.yaml
|
|
# Use environment variables for deployment-specific settings
|
|
|
|
# Speech-to-Text
|
|
# PIPELINE__STT__MODEL_SIZE=medium # tiny, base, small, medium, large-v3
|
|
# PIPELINE__STT__DEVICE=cuda # cuda or cpu
|
|
# PIPELINE__STT__COMPUTE_TYPE=float16
|
|
# PIPELINE__STT__BEAM_SIZE=5
|
|
|
|
# Text-to-Speech
|
|
# PIPELINE__TTS__ENGINE=chatterbox # chatterbox, coqui (fallback)
|
|
# PIPELINE__TTS__DEVICE=cuda
|
|
# PIPELINE__TTS__SAMPLE_RATE=24000
|
|
|
|
# Voice Activity Detection
|
|
# PIPELINE__VAD__SILENCE_DURATION=0.3 # Seconds of silence to detect speech end
|
|
# PIPELINE__VAD__CHUNK_SIZE=512 # Samples per VAD check
|
|
|
|
# Smart Turn Detection
|
|
# PIPELINE__TURN__COMPLETION_THRESHOLD=0.7 # Probability threshold (0.0-1.0)
|
|
# PIPELINE__TURN__WAIT_TIMEOUT=3.0 # Max wait after silence
|
|
|
|
# Relevance Filter
|
|
# PIPELINE__RELEVANCE__DEFAULT_SENSITIVITY=medium # low, medium, high
|
|
# PIPELINE__RELEVANCE__CACHE_SIZE=100
|
|
|
|
# Transcript Manager
|
|
# PIPELINE__TRANSCRIPT__MAX_AGE_SECONDS=90.0
|
|
# PIPELINE__TRANSCRIPT__MAX_ENTRIES=20
|
|
|
|
# ============================================================================
|
|
# Logging
|
|
# ============================================================================
|
|
# LOGGING__LEVEL=INFO # DEBUG, INFO, WARNING, ERROR
|
|
# LOGGING__TRACK_LATENCY=true
|
|
|
|
# ============================================================================
|
|
# Agent Configuration (OPTIONAL OVERRIDES)
|
|
# ============================================================================
|
|
# AGENTS__DEFAULT=jarvis # jarvis or sage
|
|
|
|
# ============================================================================
|
|
# Notes
|
|
# ============================================================================
|
|
# - Keep this file (.env) out of version control (already in .gitignore)
|
|
# - Never commit secrets to git
|
|
# - Use separate .env files for development/production
|
|
# - Environment variables override config.yaml settings
|
|
# - Variable format: SECTION__SUBSECTION__KEY=value (double underscores)
|