Audiobook creation app supporting too many TTS models (Qwen3-TTS, OmniVoice, VibeVoice, etc), focused on high-quality output. Plus audio-synced reader app and standalone server component.

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

Single-file C++ TTS runtime for Pocket TTS with ONNX Runtime — voice cloning, streaming, HTTP server, FFI C API

Fast, local, OpenAI-compatible TTS server with voice cloning support powered by Kyutai's Pocket TTS

WASM ONNX build of Pocket TTS with voice cloning adapted from pocket-tts-server to run as a Deno server instead of in the browser

A TTS that fits in your CPU (and pocket)

Seshat-TTS is an accessibility tool that provides real-time audio synthesis for games and apps. It also features a voice manager capable of cloning voices based on user presets.

GPU-enhanced Pocket TTS with Remotion + TikTok captions

OVOS TTS plugin for Pocket TTS — lightweight CPU-only TTS by Kyutai

Spring Boot app that generates an audio from text using ONNX Runtime and a text-to-speech model

Use key commands to direct your voice to any app or service you require, local or remote.

🎤 Clone voices locally with Pocket TTS OpenAPI - GPU. Enjoy free, high-quality voice synthesis, and precise timestamps without cloud reliance.

Agent skill that speaks replies aloud with Kyutai Pocket TTS - fast time-to-first-word, runs on CPU with zero config, clone any voice

Jarvis, is a Python-based personal AI assistant designed to provide real-time interaction through persistent memory, dual AI model support, and natural text-to-speech output.

Desktop app for PocketTTS with voice cloning audiobook creation, PDF/EPUB/URL import, smart chunking, and MP3 export. Runs entirely on CPU

Native iOS (SwiftUI) mindfulness app — 3 guided breath meditations in 4 voices (EN/中文), background-safe audio, adjustable length, and background music from your library. iPhone-only, fully offline.

Native SwiftUI client for a self-hosted Odysseus AI chat server — on-device Whisper STT, neural TTS (pt-BR), image vision, agent mode, web/deep search, and 10 productivity spaces. iPhone/iPad/Mac. PolyForm Noncommercial.

Pocket TTS Setup for Windows. Easy to Use.

Enable real-time voice cloning and AI chatting with a lightweight server using just 20 seconds of audio and an OpenAI-compatible API.

Local test bench for Kyutai Pocket TTS — a 100M-param, CPU-only, MIT text-to-speech model. Pick a voice and hear it synthesized on your CPU, or start a live voice call. Next.js UI + Python sidecar.