A lightweight, offline Android Text-to-Speech (TTS) engine enabling seamless system-wide voice cloning and high-fidelity text reading. / 运行在安卓本地的轻量级文字转语音 (TTS) 引擎，支持离线发音人提取、零门槛音色克隆与双擎系统级全局听书。

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

基於 OpenBMB VoxCPM2 模型的離線語音合成與聲音複製桌面工作站（支援即時錄音、語音設計與極限複製） An offline desktop workstation GUI for VoxCPM2 voice synthesis, featuring voice design, speaker cloning, and live voice recording.

CLI tool and HTTP server for offline TTS engines (gTTS, Piper, Silero, Coqui, Bark, Kokoro)

Local, portable GUI for Qwen3-TTS. Optimized for NVIDIA RTX 50 Series (CUDA 12.8). One-click install.

Automatic video translator and dubber using Whisper, XTTS v2 for voice cloning, and Ollama for local LLM translation. Supports 100+ languages.

本地曼波配音，文字转语音工具，利用本地 NVIDIA 显卡运行，无需调用第三方API，开箱即用

LocalVoice TTS AI lets you type dialog lines, assign a different voice to each line, preview them one by one, and combine everything into a single audio file — ready to download. No internet required. No subscription. No data leaves your computer. Ever. ---

🎙️ Agent Skill — Offline zero-shot voice cloning with Qwen3-TTS 0.6B. Drop a reference audio + text, get cloned speech. CPU/MPS/CUDA, 10 languages.

create audio books from pdfs with one click , available on windows , linux, mac

Portable, fully offline Text-to-Speech (TTS) client built with Python and Tkinter. This application combines the power of **Piper TTS** and **Supertonic TTS** engines to deliver high-quality, lightning-fast speech synthesis directly on your device, without requiring an internet connection, cloud services, or external API keys.

An Android app that greets you by your car's name every time you connect to Android Auto — with offline AI voices powered by Sherpa-ONNX and Kokoro TTS.

Offline Chinese and English local TTS CLI/API with sherpa-onnx, Matcha TTS, Docker, and Codex/Obsidian hooks.

NeuralVoice Studio is a next-generation, open-source AI voice generator delivering hyper-realistic speech in 85 languages and dialects. Engineered for efficiency, it runs smoothly on low-end PCs without sacrificing audio quality. Perfect for content creators, educators, and developers seeking a private, offline TTS solution.

🎙️ Lightweight offline Python TTS engine. Thread-safe, CLI-ready, and modular. Speak text locally or save to disk with pyttsx3.

A powerful, offline-first Text-to-Speech (TTS) writing assistant and document reader. Features dynamic word-by-word dictation delays, audio notification bells, and a distraction-free sentence reading mode built purely with Vanilla web technologies.

Offline Nepali (and Nepanglish) text-to-speech for edge devices. CPU-only, streamable, runs on a Raspberry Pi 4. Built on Piper, Sherpa-ONNX, and AI4Bharat IndicXlit.

Give Claude Code a voice — local, bilingual (ES/EN) text-to-speech that reads responses aloud as they stream. Kokoro ONNX, no API keys, no cloud.

CPU speech-synthesis engine for Balachky. Ukrainian TTS, offline, source preview.

Zonos-v0.1 text-to-speech(TTS) model trained on more than 200k hours of varied multilingual speech, additional support for converting pdf into audio-books --- find original release repo of zonos link below