This is a pre-trained MMS-TTS (Massively Multilingual Speech Text-to-Speech) model for English, based on the VITS architecture. It allows developers to synthesize high-quality speech from text using the Transformers library. The model is part of Meta's effort to support speech technologies for thousands of languages, with weights available for local or cloud inference.
In the Text to speech space, Mms Tts Eng takes a focused approach. It focuses on generating natural-sounding speech audio from English text. Mms Tts Eng is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web, the command line, and API.
It is developed by Meta (United States). Key capabilities include text-to-Speech, Multilingual TTS, and VITS Model.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do