Morning Edition · Thursday, November 12, 2026Published at 1:18 AM EST · New York

Zyphra releases ZONOS3-Mini, an Apache-licensed voice-cloning model with 100 million active parameters that runs in a browser

The sparse mixture-of-experts text-to-speech model clones a voice from a sample of up to one minute and runs in real time on phones and laptops, and Zyphra ranks it first among open models on its own benchmarks.

Zyphra has published ZONOS3-Mini, a compact text-to-speech (TTS) model built to run in real time on phones, laptops and in a browser, the Russian-language channel AI ML Big Data reported. It clones a voice from a recording of up to one minu…