ZONOS3-Mini is an open Apache-2.0 voice cloning text-to-speech model that runs in real time in a browser, on a laptop or on a phone
ZONOS3-Mini, released by Zyphra on 9 November 2026, is a compact open text-to-speech model with voice cloning and voice design, under the Apache 2.0 licence. It has 800 million parameters with about 100 million active per token, and runs in real time in a browser through WebGPU, on laptops and on phones.
What it does
You clone a voice from a reference clip of up to 60 seconds, or design a character by age, accent and vocal texture, and steer emotion, pace and delivery down to single words; it writes 44.1 kHz audio, up to 10 minutes per generation, and ships 27 default voices. Zyphra reports under 570 ms to first audio in the browser on a Pixel 9 and under 150 ms on an M3 MacBook Air.
Worth knowing
The browser studio downloads the model on the first visit and needs a browser with WebGPU; there are also a CUDA server, an MLX server for Apple Silicon, a C++/ggml CLI for CPU, CUDA, Metal or Vulkan, and SGLang serving with an OpenAI-compatible speech endpoint. Text normalisation covers English, Mandarin, Japanese, Korean, German, Spanish, French, Italian and Portuguese; other languages pass through as written. A hosted version is on Zyphra Cloud.