initial_commit

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.10-slim
+WORKDIR /app
+RUN apt-get update && apt-get install -y \
+    libsndfile1 \
+    ffmpeg \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+
+COPY . .
+RUN pip install -e .
+EXPOSE 7860
+WORKDIR /app/demo
+CMD ["python3", "vibevoice_realtime_demo.py", "--model_path", "../models/VibeVoice-Realtime-0.5B", "--port", "7860", "--device", "cpu"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Microsoft
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

SECURITY.md

@@ -0,0 +1,14 @@
+<!-- BEGIN MICROSOFT SECURITY.MD V1.0.0 BLOCK -->
+
+## Security
+
+Microsoft takes the security of our software products and services seriously, which
+includes all source code repositories in our GitHub organizations.
+
+**Please do not report security vulnerabilities through public GitHub issues.**
+
+For security reporting information, locations, contact information, and policies,
+please review the latest guidance for Microsoft repositories at
+[https://aka.ms/SECURITY.md](https://aka.ms/SECURITY.md).
+
+<!-- END MICROSOFT SECURITY.MD BLOCK -->

pyproject.toml

@@ -0,0 +1,45 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "vibevoice"
+version = "0.0.1"
+authors = [
+  { name="vibevoice team", email="[email protected]" },
+]
+description = "A model for speech generation with an AR + diffusion architecture."
+readme = "README.md"
+requires-python = ">=3.9"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    # "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "torch",
+    "accelerate==1.6.0",
+    "transformers==4.51.3", # we develop this project on transformers==4.51.3, later version may not be compatible
+    "llvmlite>=0.40.0",
+    "numba>=0.57.0",
+    "diffusers",
+    "tqdm",
+    "numpy",
+    "scipy",
+    "librosa",
+    "ml-collections",
+    "absl-py",
+    "gradio",
+    "av",
+    "aiortc",
+    "uvicorn[standard]",
+    "fastapi"
+]
+
+
+[project.urls]
+"Homepage" = "https://github.com/microsoft/VibeVoice"
+"Bug Tracker" = "https://github.com/microsoft/VibeVoice/issues"
+
+[tool.setuptools.packages.find]
+where = ["."]

requirements.txt

@@ -0,0 +1,17 @@
+torch
+accelerate==1.6.0
+transformers==4.51.3
+llvmlite>=0.40.0
+numba>=0.57.0
+diffusers
+tqdm
+numpy
+scipy
+librosa
+ml-collections
+absl-py
+gradio
+av
+aiortc
+uvicorn[standard]
+fastapi