On-Device Multilingual Text-to-Speech System
7.1k 2026-05-17
supertone-inc/supertonic
Supertonic is a lightning-fast, on-device, multilingual text-to-speech system offering high-quality audio and privacy without cloud dependencies.
Core Features
Blazingly fast, real-time synthesis across various devices.
Supports 31 languages with automatic language detection.
Compact 99M-parameter model, ideal for edge devices.
Outputs studio-grade 44.1kHz audio directly.
Includes 10 inline expression tags for natural speech.
Quick Start
pip install supertonicDetailed Introduction
Supertonic is an innovative, open-weight text-to-speech (TTS) system designed for local inference, eliminating the need for cloud services or API calls. Leveraging ONNX Runtime, it delivers blazingly fast, real-time multilingual speech synthesis directly on desktop, mobile, and edge devices. Its compact model size and support for 31 languages, coupled with high-quality 44.1kHz audio output and expressive tags, make it a versatile solution for privacy-conscious, low-latency audio generation across diverse applications.