Chatterbox-TTS-Server and Dia-TTS-Server
These are ecosystem siblings—both are self-hosted TTS servers built by the same developer using different underlying models (Chatterbox vs. Dia), allowing users to choose which model better suits their use case rather than use them together.
About Chatterbox-TTS-Server
devnen/Chatterbox-TTS-Server
Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runs accelerated on NVIDIA (CUDA), AMD (ROCm), and CPU.
Supports three distinct Chatterbox model variants—Original, Multilingual (23 languages), and Turbo (350M parameters with single-step audio diffusion)—all hot-swappable via UI dropdown without server restart. Built on FastAPI with intelligent text chunking for audiobook-scale processing, generation seeds for reproducible voices, and native paralinguistic tags (`[laugh]`, `[cough]`) in Turbo for expressive agent narratives. Includes portable Windows mode with embedded Python runtime for zero-dependency deployment.
About Dia-TTS-Server
devnen/Dia-TTS-Server
Self-host the powerful Dia TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), support for SafeTensors/BF16, voice cloning, dialogue generation, and GPU/CPU execution.
Supports hot-swappable switching between three Dia model variants (1.6B, Dia2-1B, Dia2-2B) with background loading, enabling multi-model inference without server restarts. Built on FastAPI with intelligent text chunking for handling large inputs, per-speaker voice conditioning (Dia 2), and a model registry architecture that gracefully handles optional package installations via defensive imports.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work