- Removed the backend client compatibility wrapper and associated methods to streamline backend integration. - Updated session management to utilize control plane gateways and runtime configuration providers. - Adjusted TTS service implementations to remove the EdgeTTS service and simplify service dependencies. - Enhanced documentation to reflect changes in backend integration and service architecture. - Updated configuration files to remove deprecated TTS provider options and clarify available settings.
36 lines
559 B
Plaintext
36 lines
559 B
Plaintext
# Web Framework
|
|
fastapi>=0.109.0
|
|
uvicorn[standard]>=0.27.0
|
|
websockets>=12.0
|
|
python-multipart>=0.0.6
|
|
|
|
# WebRTC (optional - for WebRTC transport)
|
|
aiortc>=1.6.0
|
|
|
|
# Audio Processing
|
|
av>=12.1.0
|
|
numpy>=1.26.3
|
|
onnxruntime>=1.16.3
|
|
|
|
# Configuration
|
|
pydantic>=2.5.3
|
|
pydantic-settings>=2.1.0
|
|
python-dotenv>=1.0.0
|
|
toml>=0.10.2
|
|
pyyaml>=6.0.1
|
|
|
|
# Logging
|
|
loguru>=0.7.2
|
|
|
|
# HTTP Client
|
|
aiohttp>=3.9.1
|
|
|
|
# AI Services - LLM
|
|
openai>=1.0.0
|
|
dashscope>=1.25.11
|
|
|
|
# Microphone client dependencies
|
|
sounddevice>=0.4.6
|
|
soundfile>=0.12.1
|
|
pyaudio>=0.2.13 # More reliable audio on Windows
|