Supertonic
supertone-oss-archive/supertonicReviewed by AI
Checked by RepoPicks Radar on
What is Supertonic?
Supertonic is a small text-to-speech model with example code for Python, Node.js, browser, Java, C++, C#, Go, Swift, iOS, Rust and Flutter. It reads text aloud in 31 languages and saves a 44.1 kHz WAV file, running on the processor alone, with no graphics card and no internet once the files are downloaded. It is not a finished program: you clone the repository, download the model from Hugging Face and run an example. The company ended the project and the repository is archived.
Supertonic is free and open source (MIT) and can replace ElevenLabs, Murf, and Speechify.
How easy is it to install Supertonic?
C · install 1 or 2 tools · Windows
- Windows C
- macOS C
- Linux C
The documented path is the same on Windows, Mac and Linux: install Python 3.11, create a virtual environment, download the model files with the Hugging Face tool and run "python example_onnx.py" from the py/ folder. The examples for Go, Java, C# and C++ need extra runtimes on top of that.
Supertonic on GitHub
- Stars
- 13,752on Nov 10, 2026
- Downloads
- —all releases
- Growth
- —no gain in the last reading
Stars over time
Facts
- Runs on
- Windows, macOS, Linux
- You need to install
- Python
- Disk space
- not determined
- Accounts or keys
- None
- Cost
- Free
- License
- MIT (Permissive)
- Can replace
- ElevenLabs, Murf, Speechify, Fish Audio
- Last change on GitHub
- Sep 9, 2026
Supertonic risk signals (8)
- AttentionOwner account created recently
Owner account created 62 days ago
automatic check
- AttentionDownload links to file-sharing sites
README links to https://drive.google.com/file/d/1eancUOhiSXCVoTu9ddh4S-OcVQaWrPV-/view?usp=sharing
automatic check
- Attentionmodel license restricts use
README.md "License": "This project's sample code is released under the MIT License" but "The accompanying model is released under the OpenRAIL-M License". The voice model, which is the useful part, has use restrictions that the MIT code does not.
AI review
- Attentionproject discontinued by company
README.md opens with "This repository is archived. Development and support have ended... No updates, bug fixes, security patches, or support will be provided", and the preserved notice says "Voice Builder will no longer be accessible after August 31, 2026". The hosted demos and the custom-voice service are gone.
AI review
- InfoRepository archived
The repository is archived (read-only, no longer maintained)
automatic check
- Infomodel files downloaded separately
The Quick Start downloads the weights with "hf download supertone-oss-archive/supertonic-3 --revision aafc6e32... --local-dir assets". The repository itself has no model, so the audio quality depends on files fetched from Hugging Face.
AI review
- Infono voice cloning
README.md: "This open-weight repository focuses on fixed-voice, local TTS and does not include an official voice-cloning pipeline." You get the preset voices, not your own voice.
AI review
- Infocomparisons made by the authors
The tables with green checks for Supertonic and crosses for ElevenLabs, OpenAI and Gemini, and the accuracy charts, were produced by the project authors; the sample audio files sit on Google Drive links.
AI review
Evidence is shown in its original language.
What Radar could not check about Supertonic
- How natural the voices sound in each of the 31 languages
- The real speed and memory use on an ordinary computer or a Raspberry Pi
- The total disk space after downloading the model files
- Whether the examples for Node.js, browser, Java, C++, C#, Go, Swift, Rust and Flutter still build today
- What the OpenRAIL-M license allows for commercial work