ChatTTS-ui and chatterbox-api
These are ecosystem siblings—ChatTTS-ui is a web interface for the ChatTTS synthesis engine, while chatterbox-api wraps a different TTS backend (Chatterbox-TTS) in an OpenAI-compatible API, both serving as different implementation approaches to the same self-hosted TTS server problem.
About ChatTTS-ui
jianchang512/ChatTTS-ui
一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface that uses ChatTTS to synthesize text into speech, along with support for external API interfaces.
Supports voice timbre customization through numeric seed values and linguistic control markers (laughter, pauses, breaks), with optional GPU acceleration via CUDA/ROCm for compatible hardware. Built on PyTorch with FFmpeg integration for audio processing, deployable via Docker containers (CPU/GPU variants) or source installation across Windows, Linux, and macOS. Exposes a POST-based REST API endpoint (`/tts`) returning WAV files with configurable synthesis parameters (temperature, top-p sampling, voice selection).
About chatterbox-api
jianchang512/chatterbox-api
一个基于 Chatterbox-TTS的文字转语音（TTS）服务。提供与 OpenAI TTS 兼容的 API 接口并支持声音克隆，附带简洁的 Web 用户界面。
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work