This repository is archived. Development and support have ended.

The code remains available for reference under the terms of the LICENSE. No updates, bug fixes, security patches, or support will be provided, and issues and pull requests are no longer monitored. The software is provided "AS IS" as set forth in the license, without any warranty or ongoing responsibility of the original authors.

Archive locations

The source code is preserved under the supertone-oss-archive GitHub organization. Model downloads now use the supertone-oss-archive Hugging Face namespace:

• Source code
• Supertonic 3 weights
• Supertonic 2 weights
• Supertonic 1 weights

See Quick Start to download the archived models and run locally. Code and model weights retain their respective licenses. This archive does not include hosted demos or Voice Builder services.

Supertonic — Lightning Fast, On-Device, Accurate TTS

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

✨ Highlights

• ⚡ Blazingly Fast — Low-latency, real-time synthesis across desktop, browser, mobile, and edge — fast enough to turn an entire webpage into audio in under a second
• 🌍 31-Language Multilingual — Synthesize directly from text across 31 languages, or pass lang="na" to let Supertonic process the text language-agnostically when you don't know the input language — no separate language adapters needed
• 🪶 99M-Parameter Open-Weight Model — A compact, fully open-weight checkpoint — a fraction of the size of 0.7B–2B class open TTS systems — for smaller downloads, faster cold starts, and lower memory footprint
• 📱 Edge-Device Ready — Runs locally on desktop, mobile, browsers, and resource-constrained hardware like Raspberry Pi or e-readers, with zero network dependency, complete privacy, and no GPU required
• 🔊 44.1kHz High-Quality Audio — Outputs studio-grade 44.1kHz 16-bit WAV directly, ready for production playback without any external upsampler
• 🎭 Expression Tags — 10 inline tags (e.g. <laugh>, <breath>, <sigh>) bring natural human nuance into generated speech without prompt engineering or reference audio
• 🛠️ Multi-Runtime SDKs — Ready-to-use examples through ONNX Runtime across Python, Node.js, Browser (WebGPU), Java, C++, C#, Go, Swift, iOS, Rust, and Flutter

🌍 Supported Languages (31)

Arabic (ar), Bulgarian (bg), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Finnish (fi), French (fr), German (de), Greek (el), Hindi (hi), Hungarian (hu), Indonesian (id), Italian (it), Japanese (ja), Korean (ko), Latvian (lv), Lithuanian (lt), Polish (pl), Portuguese (pt), Romanian (ro), Russian (ru), Slovak (sk), Slovenian (sl), Spanish (es), Swedish (sv), Turkish (tr), Ukrainian (uk), Vietnamese (vi)

Not sure which language your text is in? Pass lang="na" and Supertonic will handle the input in a language-agnostic way — no explicit language tag required.

Quick Start

Use the examples in this repository with model files downloaded explicitly from the archive. No Hugging Face login, hosted demo, or original Supertone service is required. These instructions use Supertonic 3.

1. Clone the source and install the download tool

Use Python 3.11 in a virtual environment:

git clone https://github.com/supertone-oss-archive/supertonic.git
cd supertonic
python3.11 -m venv .venv
source .venv/bin/activate
python -m pip install huggingface_hub

On Windows, activate the environment with .venv\Scripts\Activate.ps1 in PowerShell.

2. Download the archived model

hf download supertone-oss-archive/supertonic-3 \
  --revision aafc6e32416a594460b32413efc49d7fe4ce6d46 \
  --local-dir assets

This downloads the ONNX models, configuration, and preset voice styles to assets/. The revision pins the archived snapshot. Git LFS is not needed for this download method. See Models & Versions for the archived Supertonic 1 and 2 weights.

3. Generate speech locally

python -m pip install -r py/requirements.txt
cd py
python example_onnx.py --n-test 1 --text "This speech was generated locally with the archived Supertonic model." --lang en

The generated WAV file is saved in py/results/. After dependencies and models have been downloaded, this example performs inference locally without a network connection. See Python examples for voice selection, batch synthesis, and other options.

Optional Python SDK

Older releases of the supertonic Python package may still use the original Supertone Hugging Face namespace for automatic downloads. Download assets/ as above and pass model_dir with auto_download=False instead.

To use the preserved SDK source with Supertonic 3 support, run these commands from the repository root in the same virtual environment:

python -m pip install "git+https://github.com/supertone-oss-archive/supertonic-py.git@df0f9686dac7fbbde391b759e2ee5286a3737622"
python py/example_pypi.py

The SDK example uses the local assets/ directory and does not download models. The archived local server guide is available for reference; the ONNX example above is the default archive setup.

Getting Started in Other Runtimes

Download the same assets/ directory from the repository root before running the examples below. The language examples read these local files.

Some language examples need native runtimes: - Go: install the ONNX Runtime C library. On macOS, brew install onnxruntime. - Java: use a JDK, not just a JRE. On macOS, brew install openjdk@17. - C#: targets .NET 9 and allows major-version roll-forward.

Other Runtime Examples

cd nodejs
npm install
npm start

cd web
npm install
npm run dev

cd java
mvn clean install
mvn exec:java

cd cpp
mkdir build && cd build
cmake .. && cmake --build . --config Release
./example_onnx

cd csharp
dotnet restore
dotnet run

cd go
go mod download
go run example_onnx.go helper.go

cd swift
swift build -c release
.build/release/example_onnx

cd rust
cargo build --release
./target/release/example_onnx

cd ios/ExampleiOSApp
xcodegen generate
open ExampleiOSApp.xcodeproj

Technical Details

• Runtime: ONNX Runtime for cross-platform inference
• Browser Support: onnxruntime-web for client-side inference
• Batch Processing: Supports batch inference for improved throughput
• Audio Output: Outputs 44.1kHz 16-bit WAV files

Performance Highlights

Supertonic 3 is designed for practical on-device inference: compact enough to run locally, while staying competitive with much larger open TTS systems.

Reading Accuracy

Evaluated on the Minimax-MLS-test benchmark, Supertonic 3 stays within a competitive WER/CER range against much larger open TTS models such as VoxCPM2, while preserving a lightweight on-device deployment path. Asterisked languages (*) use CER; the others use WER.

Supertonic 2 to Supertonic 3

Compared with Supertonic 2, Supertonic 3 reduces repeat and skip failures, improves speaker similarity across the shared-language set, and expands language coverage from 5 to 31 languages. It keeps the v2-compatible public ONNX interface, so existing integrations can move to v3 with the same inference contract.

Runtime Footprint

Supertonic 3 runs fast on CPU, even compared with larger baselines measured on A100 GPU, and uses substantially less memory. The open-weight fixed-voice setting does not require a GPU, which makes local, browser, and edge deployment much easier.

Model Size

At about 99M parameters across the public ONNX assets, Supertonic 3 is much smaller than 0.7B to 2B class open TTS systems. The smaller model size is a practical advantage for download size, startup time, and on-device inference.

Voice Cloning

This open-weight repository focuses on fixed-voice, local TTS and does not include an official voice-cloning pipeline. If you want to bring your own voice to local Supertonic deployment, Voice Builder turns a short reference recording into version-specific JSON files for Supertonic 2 and Supertonic 3, so the same custom voice can move with you across supported Supertonic versions.

For a managed creation workflow, Supertonic 3 is now officially available in Supertone Play and the Supertone API. Use them when you want hosted content creation tools, diverse commercially usable preset voices, zero-shot voice cloning, or API-based integration without managing local model files. You can also listen to Supertonic 3 zero-shot samples on the official showcase.

Demo

Run locally: Follow Quick Start with the archived weights.

Raspberry Pi

Watch Supertonic running on a Raspberry Pi, demonstrating on-device, real-time text-to-speech synthesis:

https://github.com/user-attachments/assets/ea66f6d6-7bc5-4308-8a88-1ce3e07400d2

E-Reader

Experience Supertonic on an Onyx Boox Go 6 e-reader in airplane mode, achieving an average RTF of 0.3× with zero network dependency:

https://github.com/user-attachments/assets/64980e58-ad91-423a-9623-78c2ffc13680

Chrome Extension

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:

https://github.com/user-attachments/assets/cc8a45fc-5c3e-4b2c-8439-a14c3d00d91c

Programming Language Support

We provide ready-to-use TTS inference examples across multiple ecosystems:

For detailed usage instructions, please refer to the README.md in each language directory.

Natural Text Handling

Supertonic is designed to handle complex, real-world text inputs that contain natural prose, punctuation, abbreviations, and proper nouns.

These historical audio samples are hosted externally and are not maintained as part of this archive.

Overview of Test Cases:

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

Models & Versions

Version-specific branches and tags preserve historical code. Their old download instructions may reference the original organization; use the model archives below. The Quick Start above uses Supertonic 3 and its matching code on main.

Citation

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.

@article{kim2025supertonic,
  title={SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System},
  author={Kim, Hyeongju and Yang, Jinhyeok and Yu, Yechan and Ji, Seunghun and Morton, Jacob and Bous, Frederik and Byun, Joon and Lee, Juheon},
  journal={arXiv preprint arXiv:2503.23108},
  year={2025},
  url={https://arxiv.org/abs/2503.23108}
}

Length-Aware RoPE: Text-Speech Alignment

This paper presents Length-Aware Rotary Position Embedding (LARoPE), which improves text-speech alignment in cross-attention mechanisms.

@article{kim2025larope,
  title={Length-Aware Rotary Position Embedding for Text-Speech Alignment},
  author={Kim, Hyeongju and Lee, Juheon and Yang, Jinhyeok and Morton, Jacob},
  journal={arXiv preprint arXiv:2509.11084},
  year={2025},
  url={https://arxiv.org/abs/2509.11084}
}

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.

@article{kim2025spfm,
  title={Training Flow Matching Models with Reliable Labels via Self-Purification},
  author={Kim, Hyeongju and Yu, Yechan and Yi, June Young and Lee, Juheon},
  journal={arXiv preprint arXiv:2509.19091},
  year={2025},
  url={https://arxiv.org/abs/2509.19091}
}

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching

This paper describes the RobustSpeechFlow technique for improving the robustness and quality of text-to-speech generation by optimizing flow-matching trajectories against data variability

@misc{yang2026robustspeechflowlearningrobusttexttospeech,
      title={RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching}, 
      author={Jinhyeok Yang and Hyeongju Kim and Yechan Yu and Joon Byun and Frederik Bous and Juheon Lee},
      year={2026},
      eprint={2605.22083},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2605.22083}, 
}

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.