sherpa-onnx is a powerful inference engine that supports multiple TTS models (including MeloTTS). It is built-in supported and uses CPU inference by default.

Abstract: This work presents a browser-based tool that turns math-heavy PDFs into clear, human-sounding speech. Built for blind and low-vision readers as well as auditory learners, it speaks equations ...

Text-to-Speech, or TTS, is a technology that converts written text into spoken audio. It is widely used in voice assistants, accessibility tools, alert systems, kiosks, and smart devices. On computers ...