ChatTTS-ui is a local web interface and API wrapper around the ChatTTS speech synthesis system, designed to make advanced TTS models easy to use from a browser. It runs a small backend server (Python + Torch + ffmpeg) and exposes a simple webpage where you can type text, adjust parameters, and generate audio. The project supports Chinese, English, and mixed text with digits and control symbols, making it suitable for bilingual content and numerically heavy text like announcements or prompts. From version 0.96 onward, ffmpeg installation is required for deployment, and previous CSV/PT voice tables are no longer valid, so users instead work with updated “voice value” parameters. For convenience, there is a prepackaged Windows build: you download a release archive, extract it, and double-click app.exe to start the web UI, which opens on localhost:9966.
Features
- Local web UI for ChatTTS models, supporting Chinese, English, mixed digits, and control symbols
- Windows prebuilt package (app.exe) plus Docker-based and source deployments for Linux and macOS
- REST-style API endpoints so other programs can call TTS over HTTP
- Optional GPU acceleration via CUDA or ROCm with CPU-only fallback for environments without powerful GPUs
- Automatic or manual model download into an asset directory to handle network constraints
- Cross-platform setup instructions and helper scripts (run.bat, docker-compose.*.yaml) for rapid deployment
Project Samples
