Zonos

Free

Expressive 1.6B open model with high-fidelity cloning.

Open-SourceVoice CloningExpressive

Overview

Zonos from Zyphra is a 1.6B parameter open model trained on a large speech corpus, offering high-fidelity voice cloning and control over speaking rate, pitch and emotion. It supports several languages and outputs 44kHz audio. The Apache-2.0 release makes it usable in commercial products.

What makes Zonos special?

Focus: High-fidelity expressive cloning.
Availability: Free & Open-Source (Apache-2.0).
Use cases: Expressive cloning and multilingual narration.

Visit official site

Related free models

Chatterbox

A lightweight, fast TTS model built on LLaMA.

Dia

A 1.6B parameter TTS model from Nari Labs.

Kokoro

An 82M parameter TTS model by Hexgrad.

Back to directory