# ZONOS3-Mini — Zyphra's open TTS model clones voices in real time

> An Apache-2.0 speech model small enough to clone a voice in real time on a phone or in a browser tab.

- Org: Zyphra
- Date: 2026-11-09
- Category: model
- Source: https://zyphra.com/our-work/zonos3-mini
- Canonical page: https://ai-tldr.dev/releases/zyphra-zonos3-mini/

## In short

ZONOS3-Mini is Zyphra's open-weight text-to-speech model: an 800M-parameter MoE with about 100M active, Apache 2.0, 43 languages and zero-shot voice cloning. It runs in real time on laptops, phones and in the browser.

## What it is

ZONOS3-Mini is a compact open-weight text-to-speech model from Zyphra that clones a voice from a short audio sample and speaks 43 languages. Beyond cloning, it can design a voice from age, accent and vocal texture, and it lets you steer emotion, pace and delivery down to single words. The weights are on Hugging Face under Apache 2.0.

## How it works

Under the hood the model is a sparse mixture of experts: 800M parameters in total, but only about 100M are active for each token. It predicts 15 Hz audio tokens from Zyphra's own ZAC-1 codec and outputs 44.1 kHz audio, up to 10 minutes per generation. Zyphra trained it on 112 NVIDIA H100s in 2.5 days and post-trained it with DPO and then GRPO.

## Why it matters

Local, real-time voice cloning used to mean a GPU server. Zyphra reports time to first audio under 150 ms on an M3 MacBook Air and under 570 ms in a browser on a Pixel 9, and on an H100 it serves 80 ms first audio with 8 concurrent requests. That makes on-device voice agents and offline narration practical, with day-0 support in SGLang, vLLM, Ollama and llama.cpp.

## Who it's for

developers building voice agents and speech apps

## Try it

ollama run hf.co/Zyphra/ZONOS3-Mini

## Links

- [Announcement](https://zyphra.com/our-work/zonos3-mini)
- [Model Card](https://huggingface.co/Zyphra/ZONOS3-Mini)
- [GitHub](https://github.com/Zyphra/ZONOS3-Mini)
- [HF Trending](https://huggingface.co/models?sort=trending)