pyproject.toml

[project]
name = "whisper-writer"
version = "0.2.0"
description = "A small speech-to-text app that allows you to write with your voice and optionally clean up your dictated text through LLMs. "
authors = [
    {name = "savbell"},
    {name = "Thomas Frank"},
    {name = "dariox1337"},
    {name = "GrahamboJangles"},
    {name = "McEsgow"},
    {name = "KernAlan"},
    {name = "uberkael"},
    {name = "josher19"},
    {name = "Martinligabue"},
]
requires-python = ">=3.12"

dependencies = [
    # Core dependencies
    "PyQt5>=5.15.10",
    "pynput>=1.7.6",
    "sounddevice>=0.4.6",
    "soundfile>=0.12.1",
    "numpy>=1.26.4",
    "PyYAML>=6.0.1",
    "requests>=2.31.0",
    "tqdm>=4.65.0",
    "audioplayer>=0.6",
    "python-dotenv>=1.0.0",
    "keyring>=24.3.0",
    "webrtcvad-wheels>=2.0.11.post1",
    "srt>=3.5.3",
    
    # Windows-specific dependencies
    "pycaw>=20240210",
    "pywin32>=308",
    "comtypes>=1.4.10",
    
    # API integrations
    "openai>=1.28.0",
    "anthropic>=0.45.2",
    "groq>=0.18.0",
    "google-generativeai>=0.8.4",
    "google-api-core>=2.24.1",
    "google-auth>=2.38.0",
    "googleapis-common-protos>=1.67.0",

    # Local transcription and LLM support
    # Run 'pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126' AFTER 'pip install .' to install CUDA-compatible versions of torch and torchaudio
    "torch==2.6.0",
    "torchaudio==2.6.0",
    "faster-whisper>=1.1.1",
    "ctranslate2>=4.5.0",
    "vosk>=0.3.45",
    "ollama>=0.4.7",
    
    # Development tools
    "pytest>=8.0.0",
    "black>=24.1.1",
    "flake8>=7.0.0",
    "pip-tools>=7.3.0",
    "pyinstaller>=6.12.0",
]

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.metadata]
allow-direct-references = true

[tool.hatch.build.targets.wheel]
packages = ["src"]