Zonos Models by Zyphra
Zyphra releases · 2 in the last 12 months · this family litChangelog →
1 model2026
Last refreshed 2026-11-10. Next refresh: weekly.
About
Zonos is Zyphra's model line of open text-to-speech models with voice cloning.
Decision facts
- Best fit
- text to speech
- Capability starting point
- ZONOS3-Mini
- Lowest tracked input
- Not tracked
- Closest related family
- ZAYA1
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| ZONOS3-Mini | Use when the workload needs text to speech and audio. | 2026-11 | text to speechaudio | Current |
Release Timeline
1 release group2026-11
1 current
ZONOS3-Mini
Currenttext to speechaudio
Specifications(1 models)
| Model | Released | Parameters |
|---|---|---|
| ZONOS3-Mini | 2026-11 | 800M (100M active) |
