[project]
name = "voice-tts"
version = "0.1.0"
description = "Local GPU-powered real-time TTS pipeline with WebSocket API for AI agents"
requires-python = ">=3.10"
dependencies = [
"fastapi>=0.115.0",
"uvicorn[standard]>=0.32.0",
"pydantic>=2.9.0",
"pydantic-settings>=2.6.0",
"numpy>=1.26.0",
"torch>=2.4.0",
"torchaudio>=2.4.0",
"loguru>=0.7.0",
"f5-tts>=1.1.0",
"soundfile>=0.12.0",
"pydub>=0.25.0",
"tqdm>=4.66.0",
"omegaconf>=2.3.0",
"hydra-core>=1.3.0",
"safetensors>=0.4.0",
"transformers>=4.45.0",
"huggingface-hub>=0.25.0",
"vocos>=0.1.0",
"matplotlib>=3.9.0",
"unidecode>=1.3.0",
"tomli>=2.0.0 ; python_version < '3.11'",
"cached-path>=1.6.0",
"accelerate>=0.34.0",
"sentencepiece>=0.2.0",
"bitsandbytes>=0.44.0",
]
[project.optional-dependencies]
dev = [
"pytest>=8.3.0",
"pytest-asyncio>=0.24.0",
"httpx>=0.27.0",
"websockets>=13.0",
]
[project.scripts]
voice-tts = "voice_tts.main:main"
[tool.setuptools.packages.find]
where = ["src"]
[tool.pytest.ini_options]
asyncio_mode = "auto"
testpaths = ["tests"]