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.
📰 Update News
2026.01.22 - Voice Builder is now live! Turn your voice into a deployable, edge-native TTS with permanent ownership.
Voice Builder
2026.01.06 - 🎉 Supertonic 2 released with multilingual support! Now supports English (en), Korean (ko), Spanish (es), Portuguese (pt), and French (fr). Demo | Models
2025.12.10 - Added supertonic PyPI package! Install via pip install supertonic. For details, visit supertonic-py documentation
Turns any webpage into audio in under one second, delivering lightning-fast, on-device text-to-speech with zero network dependency—free, private, and effortless:
In Xcode: Targets → ExampleiOSApp → Signing: select your Team
Choose your iPhone as run destination → Build & Run
Technical Details
Runtime: ONNX Runtime for cross-platform inference (CPU-optimized; GPU mode is not tested)
Browser Support: onnxruntime-web for client-side inference
Batch Processing: Supports batch inference for improved throughput
Audio Output: Outputs 16-bit WAV files
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).
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
Note: These samples demonstrate how each system handles text normalization and pronunciation of complex expressions without requiring pre-processing or phonetic annotations.
Built with Supertonic
Project
Description
Links
TLDRL
Free, on-device TTS extension for reading any webpage
The following papers describe the core technologies used in Supertonic. If you use this system in your research or find these techniques useful, please consider citing the relevant papers:
SupertonicTTS: Main Architecture
This paper introduces the overall architecture of SupertonicTTS, including the speech autoencoder, flow-matching based text-to-latent module, and efficient design choices.
bibtex
1@article{kim2025supertonic,
2 title={SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System},
3 author={Kim, Hyeongju and Yang, Jinhyeok and Yu, Yechan and Ji, Seunghun and Morton, Jacob and Bous, Frederik and Byun, Joon and Lee, Juheon},
4 journal={arXiv preprint arXiv:2503.23108},
5 year={2025},
6 url={https://arxiv.org/abs/2503.23108}
7}
Length-Aware RoPE: Text-Speech Alignment
This paper presents Length-Aware Rotary Position Embedding (LARoPE), which improves text-speech alignment in cross-attention mechanisms.
bibtex
1@article{kim2025larope,
2 title={Length-Aware Rotary Position Embedding for Text-Speech Alignment},
3 author={Kim, Hyeongju and Lee, Juheon and Yang, Jinhyeok and Morton, Jacob},
4 journal={arXiv preprint arXiv:2509.11084},
5 year={2025},
6 url={https://arxiv.org/abs/2509.11084}
7}
Self-Purifying Flow Matching: Training with Noisy Labels
This paper describes the self-purification technique for training flow matching models robustly with noisy or unreliable labels.
bibtex
1@article{kim2025spfm,
2 title={Training Flow Matching Models with Reliable Labels via Self-Purification},
3 author={Kim, Hyeongju and Yu, Yechan and Yi, June Young and Lee, Juheon},
4 journal={arXiv preprint arXiv:2509.19091},
5 year={2025},
6 url={https://arxiv.org/abs/2509.19091}
7}
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.
-Demo-lightgrey){kind=icon}
-Models-lightgrey){kind=icon}