SupraTTS-1.0-Preview
SupraTTS-1.0-Preview is an open-weight English text-to-speech model with 1,031,754 parameters. It generates 24 kHz mono audio and is designed to run locally with a Python runtime.
What it does
A user can install the runtime and synthesize English speech from text on a local CPU.
- Availability
- Downloadable from Hugging Face
- Pricing model
- Not stated
- Deployment
- Local runtime; no network access required
- Privacy
- No network access at runtime
- Licence
- MIT for runtime and weights; bundled G2P dictionaries are Apache-2.0
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- SupraTTS-1.0-Preview is an English text-to-speech system. [1]
- The model has 1,031,754 parameters. [1]
- The checkpoint can be downloaded from Hugging Face.
- The runtime can synthesize speech locally without network access. [1]
- The output is 24 kHz mono audio. [1]
A ConvNeXt1D stack (depthwise conv, LayerNorm, pointwise layers, residual) maps the mel to a complex 513-bin spectrum, which the iSTFT turns into audio.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The runtime and weights are licensed under MIT. [1]
| **License** | MIT (runtime and weights); bundled G2P dictionaries are Apache-2.0 |
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/SupraLabs/SupraTTS-1.0-Preview
Retrieved 2026-10-28 00:27 UTC
Verified
Versions
2| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 2 | 2026-10-19 04:05 UTC | material change | pricing, deployment | Current |
| 1 | 2026-10-18 04:54 UTC | publication | None | Current |
In briefs
1- Whistle can now be tuned for a speaker or new language Daily brief 2026-10-18
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.