把 Kokoro-82M 语音合成模型封装成 OpenAI 兼容 API，用 Docker 一键部署，支持多说话人、SSML 和字幕时间戳，CPU、AMD、NVIDIA 都能跑。
把 EPUB 电子书转成有声书的 Python 工具，基于 Kokoro 语音合成模型，适合想批量制作个人音频书的人。
把 EPUB、PDF 或纯文本一键转成有声书，并生成与语音同步的字幕，适合批量制作有声内容。
面向创作者和开发者的 Gradio 语音工作台，集成多引擎 TTS、零样本声音克隆、Whisper 转写、人声分离与多语言翻译，一站式完成配音和字幕制作。
…summary: [CHANGELOG.md](https://github.com/remsky/Kokoro-FastAPI/blob/v0.10.0/CHANGELOG.md) feat(api): add ElevenLabs and Cartesia compatible websocket TTS for voice agen
…summary: [CHANGELOG.md](https://github.com/remsky/Kokoro-FastAPI/blob/v0.9.2/CHANGELOG.md) fix(normalizer): read a stray comma before a unit as a decimal separator by @bf
…eb ui tab by @remsky in https://github.com/remsky/Kokoro-FastAPI/pull/534 refactor/normalization-classes by @remsky in https://github.com/remsky/Kokoro-FastAPI/pull/528 f
…summary: [CHANGELOG.md](https://github.com/remsky/Kokoro-FastAPI/blob/v0.8.2/CHANGELOG.md) What's Changed fix: honour default voice code in split multi voice by @Christia
First CoreML port of hexgrad/Kokoro-82M with on-device bilingual (English + Japanese) free-text input. Contains: Predictor (flexible 1-256 phonemes) + Decoder buckets (12
kokoro-v1.0.onnx : (310MB): optimized f32 version from [taylorchu/kokoro-onnx](https://github.com/taylorchu/kokoro-onnx/releases/tag/v0.2.0) kokoro-v1.0.fp16.onnx : (169M