Abstract: The paper presents a new pathological text-to-speech (TTS) synthesis system that has the ability to control speech severity using latent interpolations. Recognising the difficulty of this ...

The J.A.R.V.I.S. Speech API is designed to be simple and efficient, using the speech engines created by Google to provide functionality for parts of the API. Essentially, it is an API written in Java, ...

A U.S. district court temporarily halted the University of Texas System’s enforcement of a new free speech law, siding with students who say its limits are overly broad and restrictive. The decision, ...

A federal judge’s ruling Tuesday temporarily blocks the University of Texas System from implementing parts of a new state law that limits where and when students can engage in expressive activities on ...

Alibaba researchers have unveiled Marco-Voice, a new text-to-speech (TTS) system that brings together voice cloning and emotional speech synthesis in a single framework. With Marco-Voice, Alibaba aims ...

On August 26, 2025, Microsoft released VibeVoice, an open-source text-to-speech (TTS) model built for long-form, multi-speaker audio — think scripted podcasts, training modules, and dialogue-heavy ...

Microsoft’s latest open source release, VibeVoice-1.5B, redefines the boundaries of text-to-speech (TTS) technology—delivering expressive, long-form, multi-speaker generated audio that is MIT licensed ...

Editor’s Note: This story has been updated to reflect revisions to the UT-Austin Freedom of Speech, Expression and Assembly policy. The UT System Board of Regents updated the University’s free speech ...

ElevenLabs introduces Eleven v3 (alpha), an API toolset designed to create lifelike speech experiences, now integrated by industry leaders like HeyGen and Poe. ElevenLabs has announced the release of ...

Here's a closer look at the programming behind my animatronic mouth. Using Arduino, Python, and a few open-source libraries, I take a typed sentence and convert it into an animation sequence.