WhisperSpeech

Free

An open TTS built by inverting Whisper.

Open-SourceResearchMultilingual

Overview

WhisperSpeech is an open text-to-speech system created by "inverting" OpenAI’s Whisper, trained entirely on properly licensed data. It is designed to be powerful yet easily hackable and extensible. The fully open approach appeals to researchers who want transparency end to end.

What makes WhisperSpeech special?

Focus: Whisper-inverted synthesis.
Availability: Free & Open-Source (MIT).
Use cases: Research, hacking, and fully open voice pipelines.

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