F5-TTS

Free

A fast flow-matching model with fluent voice cloning.

Open-SourceVoice CloningFast

Overview

F5-TTS is a non-autoregressive, flow-matching text-to-speech model that produces fluent, faithful speech and fast zero-shot voice cloning. It avoids the slow autoregressive loop, enabling quick inference while preserving naturalness. The open implementation has become a popular base for cloning projects.

What makes F5-TTS special?

Focus: Flow-matching speech synthesis.
Availability: Free & Open-Source.
Use cases: Voice cloning, dubbing, and real-time generation.

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