😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

基于标贝数据继续训练，同时对原本的FastSpeech2模型做了改进，引入了韵律表征以及韵律预测模块，使中文发音更生动且富有节奏

🎙️ CosyVoice All-in-One Docker - Production-ready TTS with Web UI, REST API & Voice Cloning

Web app, command-line interface and Python library for synthesizing Chinese texts into speech.

让你的 Claude Code 会说话 — 自动语音朗读中文内容，8种微软官方音色可选，实时切换，免费无需API Key，跨平台支持

Kokoro-FastAPI为基础，支持hexgrad/Kokoro-82M-v1.1-zh模型，优化中英文混读，中文语音更自然，支持 Docker 自动化化部署，支持 NVIDIA GPU 加速和 CPU 推理两种运行模式

Text-to-speech library for Rust with a unified trait interface over multiple backends (Kokoro ONNX). Part of the WaveKat voice pipeline.

A text-to-speech framework for Mardarin speech synthesis, including chinese frontend process, acoustic model, vocoder and other tools.