Private, offline AI Text-to-Speech for Android with Kokoro, KittenTTS, Pocket-tts and Piper models.

🎙️ VoxSherpa TTS Offline Neural Text-to-Speech Engine for Android ⚡ Sherpa-ONNX powered 🔊 Natural voice synthesis 📱 Fully offline processing 🚀 No cloud • No limits

A minimal Android demo app for Kokoro-TTS

Kokoro Manim Voiceover

一个基于 [Bob](https://bobtranslate.com/) 的文本转语音插件，使用 Kokoro 本地部署模型作为语音合成服务。

A unified Text-to-Speech gateway combining multiple TTS providers (Kokoro ONNX, Chatterbox TTS, OpenAI Edge TTS) with a modern React frontend and production-ready Docker deployment.

A pure Swift implementation for Kokoro TTS (Text-to-Speech) using local ONNX models, supporting multiple quantization formats and automatic cache management.

Kokoro-82m TTS ONNX Runtime inference | Gradio Demo | HuggingFace Demo | Docker

Text-to-speech generated locally in your browser. Using Svelte, Kokoro.js and Transformers.js.

Offline Kokoro-82M text-to-speech for Python — library, CLI, and a unix-socket daemon for ~13ms speech from shell scripts. Apache 2.0, CPU real-time, macOS and Linux.

Local, offline English text-to-speech synthesizer (TTS) GUI

Transforms static PDF documents into professional narrated presentations using advanced local AI.

Deliver high-quality text-to-speech in the browser with 28 voices, no installation, and support for WebGPU and CPU acceleration.