English | 简体中文

Welcome to GSVI, an inference-specialized plugin built on top of GPT-SoVITS to enhance your text-to-speech (TTS) experience with a user-friendly API interface. This plugin enriches the original GPT-SoVITS project, making voice synthesis more accessible and versatile.

• High-level abstract interface for easy character and emotion selection
• Comprehensive TTS engine support (speaker selection, speed adjustment, volume control)
• User-friendly design for everyone
• Simply place the shared character model folder, and you can quickly use it.
• High compatibility and extensibility for various platforms and applications (for example: SillyTavern)

Use our optimized fork, GSVI on GitHub, for extended functionalities and plugin compatibility. Follow the installation instructions provided.

Windows users can use our prezip, which includes pre-trained models, a Python environment, and a launcher written in Easy-Programming-Language. Download the prezip and follow the installation guide on our Yuque documentation page.

• Gradio Application: ../app.py (In the root of GSVI)

• Flask Backend Program: src/tts_backend.py
• Gradio Frontend Application: src/TTS_Webui.py
• Other Frontend Applications or Services Using Our API

• Gradio Model Management Interface: src/Character_Manager.py

For API documentation, visit our Yuque documentation page.

1. Read our documentation and usage instructions before starting.
2. Go and see our huggingface demo
3. If you encounter issues, join our community or consult the FAQ. QQ Group: 863760614

We look forward to seeing how you use GSVI to bring your creative projects to life!

This fork is a plugin for GPT-soVITS project. Some of the codes (e.g. the classic inference part) are using its original code.

Special thanks to the following projects and contributors:

• ar-vits
• SoundStorm
• vits
• TransferTTS
• contentvec
• hifi-gan
• fish-speech

• Chinese Speech Pretrain
• Chinese-Roberta-WWM-Ext-Large

• paddlespeech zh_normalization
• LangSegment

• FFmpeg
• gradio)