To make the setup easier and add a few features people are asking for here (like GPU support and long text handling), I built a self-hosted server for this model: https://github.com/devnen/Kitten-TTS-Server
The goal was a setup that "just works" using a standard Python virtual environment to avoid dependency conflicts.
The setup is just the standard git clone, pip install in a venv, and python server.py.
https://github.com/devnen/Chatterbox-TTS-Server
Built this wrapper to make Chatterbox TTS more accessible. Handles long text chunking automatically, includes voice cloning through web interface, and provides both web UI and API endpoints. Makes the promising new TTS model much easier to use for practical applications.
For anyone wanting a quick way to spin this up locally with a web UI and API access, I put together a FastAPI server wrapper around the model: https://github.com/devnen/Dia-TTS-Server
The setup is just a standard pip install -r requirements.txt (works on Linux/Windows). It pulls the model from HF automatically – defaulting to the faster BF16 safetensors (ttj/dia-1.6b-safetensors), but that's configurable in the .env. You get an OpenAI-compatible API endpoint (/v1/audio/speech) for easy integration, plus a custom one (/tts) to control all the Dia parameters. The web UI gives you a simple way to type text, adjust sliders, and test voice cloning. It'll use your CUDA GPU if you have one configured, otherwise, it runs on the CPU.
Might be a useful starting point or testing tool for someone. Feedback is welcome!