c86e323d7a
Quality-first multi-pass audiobook generation from English manuscripts. Includes: - umbraaudio/ core package (pipeline, config, voices, web review UI) - scripts/ CLI utilities + model download script - tts_server/ remote TTS server - specs/ design docs, tests/, pyproject.toml + uv.lock - Qwen3-TTS git submodule (pinned 022e286) with local demo.py UI patch saved at scripts/qwen3_tts_demo_umbra_patch.patch - .env with runtime config/secrets Excluded (see .gitignore): models/ (downloaded via scripts/download_models.sh), output/, logs/, .venv, .umbra runtime data, and book projects (DealHunterShip_*), which are committed separately.
100 lines
1.9 KiB
TOML
100 lines
1.9 KiB
TOML
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "umbraaudio"
|
|
version = "0.1.0"
|
|
description = "Quality-first multi-pass audiobook generation from manuscripts"
|
|
readme = "README.md"
|
|
license = "MIT"
|
|
requires-python = ">=3.11"
|
|
authors = [{ name = "UmbraAudio" }]
|
|
keywords = ["audiobook", "tts", "text-to-speech", "narration"]
|
|
classifiers = [
|
|
"Development Status :: 3 - Alpha",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Topic :: Multimedia :: Sound/Audio :: Speech",
|
|
]
|
|
|
|
dependencies = [
|
|
# CLI
|
|
"click>=8.1",
|
|
"rich>=13.0",
|
|
|
|
# Database
|
|
"aiosqlite>=0.19",
|
|
|
|
# Parsers
|
|
"ebooklib>=0.18",
|
|
"beautifulsoup4>=4.12",
|
|
"PyMuPDF>=1.23",
|
|
"python-docx>=1.0",
|
|
|
|
# NLP / Analysis
|
|
"booknlp>=1.0",
|
|
|
|
# LLM clients
|
|
"openai>=1.10",
|
|
"httpx>=0.25",
|
|
|
|
# TTS engines
|
|
"qwen-tts>=0.1",
|
|
"edge-tts>=6.1",
|
|
"torch>=2.6",
|
|
"torchaudio>=2.6",
|
|
|
|
# Audio processing
|
|
"librosa>=0.10",
|
|
"soundfile>=0.12",
|
|
"pydub>=0.25",
|
|
|
|
# Quality metrics
|
|
"speechmos>=0.0.1",
|
|
"openai-whisper>=20231117",
|
|
"speechbrain>=0.5",
|
|
|
|
# Web review UI
|
|
"fastapi>=0.104",
|
|
"uvicorn[standard]>=0.24",
|
|
"jinja2>=3.1",
|
|
"python-multipart>=0.0.6",
|
|
|
|
# Utilities
|
|
"numpy>=1.24",
|
|
"pydantic>=2.5",
|
|
"pydantic-settings>=2.1",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=7.4",
|
|
"pytest-asyncio>=0.21",
|
|
"pytest-cov>=4.1",
|
|
"ruff>=0.1",
|
|
"mypy>=1.7",
|
|
]
|
|
|
|
[project.scripts]
|
|
umbraaudio = "umbraaudio.cli:main"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["umbraaudio"]
|
|
|
|
[tool.ruff]
|
|
target-version = "py311"
|
|
line-length = 100
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "N", "W", "UP", "B", "A", "SIM", "TCH"]
|
|
|
|
[tool.mypy]
|
|
python_version = "3.11"
|
|
strict = true
|
|
plugins = ["pydantic.mypy"]
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
asyncio_mode = "auto"
|