About this model
A 31M-parameter English text-to-speech model with ten voices, from narrators to a pirate and a dragon: runs on a plain CPU.
Every size and format published by Gradium, largest first. Want one we don't host yet? Press Request: we add the most requested ones.
| Model | Parameters | Notes | |
|---|---|---|---|
| Phonon 40M multilingual | 40M | CC BY-NC 4.0 (non-commercial) | |
| Phonon 40M (per language) | 40M | CC BY-NC 4.0 (non-commercial) | |
| Phonon 31M EN | 31M | 8-bit GGUF here · Apache-2.0 | Hosted here |
Phonon 31M is an AI voice model by Gradium. A 31M-parameter English text-to-speech model with ten voices, from narrators to a pirate and a dragon: runs on a plain CPU.
Yes: every account gets one free try of this model, plus welcome credits. After that a run usually costs about 5 credits (1,000 credits = US$1), charged for the real GPU time.
Sign in, open this page, fill in the form and press the run button. It runs on our cloud GPUs: nothing to install, and it works on phones too.
License: Apache-2.0 (31M English model and voices). Commercial use of the outputs is allowed by the license.
All models · Not affiliated with Gradium or with AI Search.