jianchang512/ChatTTS-ui
Provides a local web interface and API for the ChatTTS model, enabling text-to-speech synthesis with support for mixed languages and numbers.
Core Features
Quick Start
docker compose -f docker-compose.gpu.yaml up -dDetailed Introduction
This project offers a user-friendly local web interface and API for the powerful ChatTTS text-to-speech model. It allows users to convert text, including mixed Chinese, English, and numbers, into natural-sounding speech directly on their own machines. With flexible deployment options like pre-packaged executables, Docker containers, and source code, it caters to various technical skill levels and environments. The integration of GPU acceleration ensures efficient processing, making it an ideal solution for developers and users seeking a private, high-quality TTS solution without relying on cloud services.