supertonic

An open-source read-along document reader server with high-quality TTS options, synchronized highlighting, and audiobook export for EPUB, PDF, DOCX, TXT, and MD.

A multi engine TTS & LLM edge computing playground with audio book features and more!

C# Generative AI SDK - Text, Image, Video and Audio supported

A command-line interface for running Supertonic TTS models using MNN.

Local AI video translation, dubbing, subtitles, and blur editing with faster-whisper, Argos Translate, Supertonic, FFmpeg, and yt-dlp

Supertonic-ZH — fast on-device Mandarin TTS (pure ONNX). Now with streaming synthesis for real-time dialogue (low first-audio latency, barge-in).

Sample code to call TTS API: Supertonic, Kokoro, Piper

A gateway server that integrates local LLMs with the high-quality TTS engine Supertonic, providing a unified interface.

Supertonic FastAPI - High Performance OpenAI-Compatible TTS API

Open-source neural-voice audiobook player for Android. Reads any text — Royal Road, GitHub, RSS, EPUB, Wikipedia & 20+ more sources — aloud via in-process Piper, Kokoro, KittenTTS & Supertonic voices, System TTS, or optional Azure HD. Hybrid reader, AI chat per fiction, Wear OS + Android Auto.

A Chrome extension that converts web articles to speech using built-in local AI models. No cloud services, no API keys – everything runs directly in your browser.

A Chrome extension that reads web pages and PDFs aloud using Supertonic's high-quality neural TTS voices that works completely offline.

On-device, real-time multimodal AI. Multilingual voice + vision (en/ko/es/pt/fr) with camera, screen, PDF, and video — runs entirely locally.

Paper-faithful PyTorch reproduction of SupertonicTTS (arXiv 2503.23108)

Audiopub transforms any EPUB into a clean, high-quality audiobook

On-device neural TTS for React Native. 31 languages. No API keys.

🎧 Supertonic TTS ONNX Inference Openai Speech REST API

A web application that converts EPUB files to text and generates text-to-speech audio using the Supertonic-3 model. Features include multilingual support (31 languages), multiple voice styles, expression tags (, , ), configurable playback speed, and click-to-play functionality with sentence-level highlighting.

giving a voice to the voiceless.

VoxCraft — Professional TTS Studio powered by Supertonic 3. Generate studio-quality 44.1kHz voiceovers with 10 voice styles across 31 languages, running 100% locally.