Parler-TTS

Free

Advanced control over pitch, speed, and emotion.

CustomizableOpen-SourcePrompt-Controlled

Overview

Parler-TTS lets you steer the voice with a natural-language description, controlling attributes like pitch, speaking rate, reverberation and emotion. It is fully open and reproducible, with training code and datasets released by Hugging Face. This makes it a great base for experimentation and fine-tuning.

What makes Parler-TTS special?

Focus: Prompt-controlled speech.
Availability: Free & Open-Source (Hugging Face).
Use cases: Research, customisation, and expressive synthesis.

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