---
title: README
emoji: ⚡
colorFrom: green
colorTo: gray
sdk: static
pinned: false
---

# Parler-TTS

Parler-TTS is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech in the style of a given speaker (gender, pitch, speaking style, etc). It is a reproduction of work from the paper [Natural language guidance of high-fidelity text-to-speech with synthetic annotations](https://www.text-description-to-speech.com/) by Dan Lyth and Simon King, from Stability AI and Edinburgh University respectively.

Contrary to other TTS models, Parler-TTS is a fully open-source release. All of the datasets, pre-processing, training code, and weights are released publicly under a permissive license, enabling the community to build on our work and develop their own powerful TTS models.
It consists in:
* The [Parler-TTS library](https://github.com/huggingface/parler-tts) for using and training high-quality TTS models.
* The [Data-Speech repository](https://github.com/huggingface/dataspeech), for annotating speech characteristics in a large-scale setting.
* This [organization](https://huggingface.co/parler-tts), that contains the released datasets and weights.

🚨 Two new checkpoints, Parler-TTS [Mini v1]((https://huggingface.co/parler-tts/parler-tts-mini-v1)) and [Large v1](https://huggingface.co/parler-tts/parler-tts-large-v1), are out! 🚨
Trained on **45k hours of narrated audio**, they're better and faster than previous versions, and introduce **speaker consistency** across generations.
Try them out [here](https://huggingface.co/spaces/parler-tts/parler_tts) 🤗!