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
32 lines
753 B
Plaintext
32 lines
753 B
Plaintext
# ===========================================================
|
|
# Echo Voice Assistant — Dependencies
|
|
# ===========================================================
|
|
# Install with: pip install -r requirements.txt
|
|
#
|
|
# Note: For GPU-accelerated TTS, install PyTorch with CUDA
|
|
# support first: https://pytorch.org/get-started/locally/
|
|
# ===========================================================
|
|
|
|
# --- Core ---
|
|
vosk>=0.3.45
|
|
pyaudio>=0.2.14
|
|
openwakeword>=0.5.0
|
|
|
|
# --- LLM ---
|
|
openai>=1.30.0
|
|
python-dotenv>=1.0.0
|
|
|
|
# --- TTS (Qwen3-TTS) ---
|
|
# Install from source or PyPI once available:
|
|
# pip install qwen-tts
|
|
torch>=2.1.0
|
|
soundfile>=0.12.1
|
|
transformers>=4.40.0
|
|
accelerate>=0.27.0
|
|
|
|
# --- Audio Playback ---
|
|
pygame>=2.5.0
|
|
|
|
# --- Utilities ---
|
|
numpy>=1.26.0
|