Illustration, AI-generated from the story text. Tap a panel to read the story through it.

Zyphra released ZONOS3-Mini on Monday under , a text-to-speech model with about 800 million in total and 100 million active per . It clones a voice from a short clip, lets users set age, accent, emotion and pace, and covers 43 languages.

Zyphra says it runs in real time on phones and laptops and entirely in a browser through , and reports a median 80 milliseconds to first audio on one . Its quality comparisons are Zyphra's own.

Voice cloning that runs in a browser tab, with no server to refuse a request, is the case bank fraud teams have been warning about.
Zyphra's open speech model clones voices in 43 languages with 100 million active parameters and runs in a browser
Zyphra released ZONOS3-Mini on Monday under Apache 2.0, a text-to-speech model with about 800 million parameters in total and 100 million active per token. It clones a voice from a short clip, lets users set age, accent, emotion and pace, and covers 43 languages. Zyphra says it runs in real time on phones and laptops and entirely in a browser through WebGPU, and reports a median 80 milliseconds to first audio on one H100. Its quality comparisons are Zyphra's own. Voice cloning that runs in a browser tab, with no server to refuse a request, is the case bank fraud teams have been warning about. SourcesAC
Sources
- AHugging Face: Zyphra/ZONOS3-Minihuggingface.co
- CMarkTechPost: Zyphra ZONOS3-Minimarktechpost.com
This story ran in the Morning Brief of November 13th 2026.