supertonic-2

Supertonic 2 — Lightning Fast, On-Device TTS, Multilingual TTS

<p align="center"> <a href="https://huggingface.co/spaces/Supertone/supertonic-2"><img src="https://img.shields.io/badge/🤗_Demo-Hugging_Face-yellow?style=for-the-badge" alt="Demo"></a> <a href="https://github.com/supertone-inc/supertonic"><img src="https://img.shields.io/badge/💻_Code-GitHub-black?style=for-the-badge&logo=github" alt="Code"></a> </p>

Supertonic is a lightning-fast, on-device text-to-speech system designed for extreme performance with minimal computational overhead. Powered by ONNX Runtime, it runs entirely on your device—no cloud, no API calls, no privacy concerns.

What's New in Supertonic 2

Supertonic 2 extends multilingual capabilities while maintaining the same inference speed and efficiency as the original.

🌍 Multilingual Support

⚡ Same Speed, More Languages

• No speed degradation: Supertonic 2 delivers the same ultra-fast inference speed as the original—up to 167× faster than real-time
• Efficient architecture: Only 66M parameters, optimized for on-device deployment
• Cross-language consistency: All supported languages share the same model architecture and inference pipeline

Performance

We evaluated Supertonic's performance (with 2 inference steps) using two key metrics across input texts of varying lengths: Short (59 chars), Mid (152 chars), and Long (266 chars).

Metrics:

• Characters per Second: Measures throughput by dividing the number of input characters by the time required to generate audio. Higher is better.
• Real-time Factor (RTF): Measures the time taken to synthesize audio relative to its duration. Lower is better (e.g., RTF of 0.1 means it takes 0.1 seconds to generate one second of audio).

Characters per Second

Notes:
API = Cloud-based API services (measured from Seoul)
Open = Open-source models
Supertonic (M4 pro - CPU) and (M4 pro - WebGPU): Tested with ONNX
Supertonic (RTX4090): Tested with PyTorch model
Kokoro: Tested on M4 Pro CPU with ONNX
NeuTTS Air: Tested on M4 Pro CPU with Q8-GGUF

Real-time Factor

<details> <summary><b>Additional Performance Data (5-step inference)</b></summary> <br>

Characters per Second (5-step)

Real-time Factor (5-step)

</details>

License

This project’s sample code is released under the MIT License. - see the LICENSE for details.

The accompanying model is released under the OpenRAIL-M License. - see the LICENSE file for details.

This model was trained using PyTorch, which is licensed under the BSD 3-Clause License but is not redistributed with this project. - see the LICENSE for details.

Copyright (c) 2026 Supertone Inc.