zhao-kun/VibeVoiceFusion
A full-stack web application for multi-speaker voice generation and cloning built on Microsoft's VibeVoice model.
Not currently ranked — collecting fresh signals.
star history
VibeVoiceFusion is a multi-speaker synthetic speech generation system combining autoregressive and diffusion architectures. It provides a complete web interface for voice synthesis, supports LoRA fine-tuning for custom voice adaptation, and includes batch generation with VRAM optimization features. The system enables voice cloning with distinct speaker characteristics without requiring coding knowledge.
Frequently asked
- What is zhao-kun/VibeVoiceFusion?
- A full-stack web application for multi-speaker voice generation and cloning built on Microsoft's VibeVoice model.
- Is VibeVoiceFusion open source?
- Yes — zhao-kun/VibeVoiceFusion is an open-source project tracked on heatdrop.
- What language is VibeVoiceFusion written in?
- zhao-kun/VibeVoiceFusion is primarily written in Python.
- How popular is VibeVoiceFusion?
- zhao-kun/VibeVoiceFusion has 484 stars on GitHub.
- Where can I find VibeVoiceFusion?
- zhao-kun/VibeVoiceFusion is on GitHub at https://github.com/zhao-kun/VibeVoiceFusion.