d6b64d04d1
- stt.py: WakeWordListener (openWakeWord) + Transcriber (Vosk) - brain.py: Async OpenRouter streaming client with command parsing - tts.py: Qwen3-TTS engine with voice selection & instruction control - actions.py: 10 local OS commands (open_app, set_timer, search, etc.) - main.py: Async orchestrator with Phase 5 parallel TTS streaming
25 lines
1016 B
Plaintext
25 lines
1016 B
Plaintext
# ===========================================================
|
|
# Echo Voice Assistant — Environment Configuration
|
|
# ===========================================================
|
|
# Copy this file to .env and fill in your values:
|
|
# cp .env.example .env
|
|
# ===========================================================
|
|
|
|
# --- OpenRouter (required) ---
|
|
# Get your key at: https://openrouter.ai/keys
|
|
OPENROUTER_API_KEY=sk-or-v1-xxxxxxxxxxxxxxxxxxxxxxxx
|
|
OPENROUTER_MODEL=qwen/qwen-3-235b-a22b
|
|
|
|
# --- Vosk STT (optional overrides) ---
|
|
# Download models from: https://alphacephei.com/vosk/models
|
|
# Set to a local path relative to the project root
|
|
VOSK_MODEL_PATH=models/vosk-model-small-en-us
|
|
WAKE_WORD=echo
|
|
|
|
# --- Qwen3-TTS (optional overrides) ---
|
|
# Available preset voices: Ryan, Serena, Diana, etc.
|
|
# Or set a path to a 3-second .wav sample for voice cloning
|
|
QWEN_TTS_MODEL=Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
|
|
QWEN_TTS_VOICE=Ryan
|
|
QWEN_TTS_INSTRUCT=Speak clearly with a warm, friendly tone. Be natural and conversational.
|