A two-person startup by the name of Nari Labs has introduced Dia, a 1.6 billion parameter text-to-speech (TTS) model designed to produce naturalistic dialogue directly from text prompts — and one of ...

What if you could access a high-quality text-to-speech system that rivals premium platforms like ElevenLabs, but without spending a dime? Below, Universe of AI takes you through how Chatterbox, an ...

What if you could replicate any voice—your favorite actor, a loved one, or even your own—with stunning accuracy and emotional depth, all in just seconds? The world of voice cloning has long been ...

A Chinese startup called Yunshang Qulv released an open-source text-to-speech model on July 1, 2026, that does something no commercially deployed rival currently offers: it replaces a single word ...

Just in time for Halloween 2024, Meta has unveiled Meta Spirit LM, the company’s first open-source multimodal language model capable of seamlessly integrating text and speech inputs and outputs.