Parler-TTS is a lightweight text-to-speech (TTS) model developed by Hugging Face that can generate high-quality, natural-sounding speech in a given speaker style (gender, tone, speaking style, etc.). It is an open-source implementation of the paper "Natural language guidance of high-fidelity text-to-speech with synthetic annotations" by Dan Lyth and Simon King from Stability AI and the University of Edinburgh, respectively. Unlike other TTS models, Parler-TTS is fully open-source, including the dataset, preprocessing, training code, and weights. Features include: * Generation of high-quality, natural-sounding speech output * Flexible usage and deployment * Provision of a rich annotated speech dataset. Pricing: Free.