pyproject.toml

[project]
name = "indextts"
version = "2.0.0"
description = "IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech"
authors = [{ name = "Bilibili IndexTTS Team" }]
license = "LicenseRef-Bilibili-IndexTTS"
license-files = ["LICEN[CS]E*", "INDEX_MODEL_LICENSE*"]
readme = "README.md"
classifiers = [
  "Development Status :: 5 - Production/Stable",

  "Intended Audience :: Science/Research",
  "Intended Audience :: Developers",

  "Topic :: Scientific/Engineering",
  "Topic :: Scientific/Engineering :: Artificial Intelligence",

  "Natural Language :: English",
  "Natural Language :: Chinese (Simplified)",

  "Programming Language :: Python :: 3",

  "Operating System :: OS Independent",
]
requires-python = ">=3.10"
dependencies = [
  # IMPORTANT: Always run `uv lock` or `uv lock --upgrade` to resolve dependencies
  # and update the lockfile after editing anything below.
  # WARNING: Ensure that you don't have a local `uv.toml` which overrides PyPI
  # while generating the lockfile: https://github.com/astral-sh/uv/issues/15741
  "accelerate==1.8.1",
  "cn2an==0.5.22",
  "cython==3.0.7",
  "descript-audiotools==0.7.2",
  "einops>=0.8.1",
  "ffmpeg-python==0.2.0",
  "g2p-en==2.1.0",
  "jieba==0.42.1",
  "json5==0.10.0",
  "keras==2.9.0",
  "librosa==0.10.2.post1",
  "matplotlib==3.8.2",
  "modelscope==1.27.0",
  "munch==4.0.0",
  "numba==0.58.1",
  "numpy==1.26.2",
  "omegaconf>=2.3.0",
  "opencv-python==4.9.0.80",
  "pandas==2.3.2",
  "safetensors==0.5.2",
  "sentencepiece>=0.2.1",
  "tensorboard==2.9.1",
  "textstat>=0.7.10",
  "tokenizers==0.21.0",
  "torch==2.8.*",
  "torchaudio==2.8.*",
  "tqdm>=4.67.1",
  "transformers==4.52.1",

  # Use "wetext" on Windows/Mac, otherwise "WeTextProcessing" on Linux.
  "wetext>=0.0.9; sys_platform != 'linux'",
  "WeTextProcessing; sys_platform == 'linux'",
]

[project.optional-dependencies]
# To install the WebUI support, use `uv sync --extra webui` (or `--all-extras`).
webui = [
  "gradio==5.45.0",
]
# To install the DeepSpeed support, use `uv sync --extra deepspeed` (or `--all-extras`).
deepspeed = [
  "deepspeed==0.17.1",
]

[project.urls]
Homepage = "https://github.com/index-tts/index-tts"
Repository = "https://github.com/index-tts/index-tts.git"

[project.scripts]
# Set the installed binary names and entry points.
indextts = "indextts.cli:main"

[build-system]
# How to build the project as a CLI tool or PyPI package.
# NOTE: Use `uv tool install -e .` to install the package as a CLI tool.
requires = ["hatchling >= 1.27.0"]
build-backend = "hatchling.build"

[tool.uv]
# Disable build isolation when building DeepSpeed from source.
no-build-isolation-package = ["deepspeed"]

[tool.uv.sources]
# Install PyTorch with CUDA support on Linux/Windows (CUDA doesn't exist for Mac).
# NOTE: We must explicitly request them as `dependencies` above. These improved
# versions will not be selected if they're only third-party dependencies.
torch = [
  { index = "pytorch-cuda", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
]
torchaudio = [
  { index = "pytorch-cuda", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
]
torchvision = [
  { index = "pytorch-cuda", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
]

[[tool.uv.index]]
name = "pytorch-cuda"
# Use PyTorch built for NVIDIA Toolkit version 12.8.
# Available versions: https://pytorch.org/get-started/locally/
url = "https://download.pytorch.org/whl/cu128"
# Only use this index when explicitly requested by `tool.uv.sources`.
explicit = true