tiny-voca-arabic vs ZONOS3-Mini
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Speech synthesis | Speech synthesis |
| Published capabilities | A compact CPU-oriented model trained from scratch using the tiny-voca architecture and an Arabic phonetic front end. | Supports promptable voice style and speech editing. Runs locally, including on phones and in the browser. |
| Model size | 4.53M parameters | 100M active parameters |
| Access | Downloadable ONNX and PyTorch weights | Downloadable publisher checkpoint |
| Result | 24 kHz mono speech in Modern Standard Arabic | Synthesized speech |
| Operating limits | Includes one synthetic Modern Standard Arabic voice. The publisher reports about 200× real-time generation on two CPU threads. | Not published |
| Sources | Model weights · Additional documentation | Model weights |
| Inputs | Text | Text, Audio |
| Weights | Open weights · Apache-2.0 | Open weights · Apache-2.0 |
| Released | Nov 21, 2026 | Nov 9, 2026 |