Vixtts-demo
viXTTS Demo generates Vietnamese speech from text and cloned voices through a Gradio interface, with hosted and local usage options for producing audio files.

Total stars
Last 7 days
516
HostingSelf-hostable
LicenseMPL-2.0
LanguageJupyter Notebook
Last commitApr 4, 2025
Latest releaseNot available
Release frequencyNo releases
Contributors2
Stars516
Forks200
Issues16
What it does
viXTTS Demo is a Vietnamese voice-cloning and text-to-speech tool based on a fine-tuned XTTS-v2.0.3 model and the viVoice dataset. Users can enter text, generate speech in Vietnamese, and use cloned voices; the README also says other languages are offered, though their effectiveness has not been tested.
The project provides a hosted Hugging Face Space and a local Ubuntu or WSL2 workflow. Local use installs dependencies through run.sh, launches a Gradio demo, and saves generated results in an output directory. It recommends at least 16GB of RAM, 10GB of disk space, and an Nvidia GPU with 4GB of VRAM, while CPU inference is supported but slower.
Capabilities
#Text-to-speech voiceover production
#Voice cloning and design
Built with
Tools similar to Vixtts-demo
GPT-SoVITS
Audio Editing
ChatTTS
Audio Editing
Ebook2audiobook
Audio Editing
Voice-pro
Audio Editing
VoiceStudio
Audio Editing
EmotiVoice
Audio Editing