Daniil Klimov
a9001aef92
- audio: switch VAD to webrtcvad with RMS gate + fallback to RMS - audio: honor FOLLOWUP_TIMEOUT — short silence wait after bot response - llm: retry with exponential backoff on network errors and 5xx - llm: VOICE_MAX_TOKENS env (default 300) instead of hardcoded 150 - tts: optional VAD-based barge-in (BARGE_IN_ENABLED, off by default) - tts: remove dead start_barge_in_listener / was_barge_in helpers - config: drop AGENT/LUSYA_AGENT — routing happens via session_key - modes: remove unused imports, pass FOLLOWUP_TIMEOUT to follow-up record() - docs: full rewrite of README and CLAUDE.md to match current architecture
24 lines
306 B
Plaintext
24 lines
306 B
Plaintext
requests
|
|
python-dotenv
|
|
numpy<2
|
|
|
|
# Audio I/O
|
|
pyaudio
|
|
sounddevice
|
|
scipy<1.15
|
|
webrtcvad-wheels
|
|
|
|
# STT через облако
|
|
groq
|
|
|
|
# TTS
|
|
elevenlabs
|
|
|
|
# Wake word
|
|
openwakeword
|
|
|
|
# Русская морфология для нормализации текста под TTS
|
|
num2words
|
|
pymorphy3
|
|
pymorphy3-dicts-ru
|