A new, open source text-to-speech model called Dia has arrived to challenge ElevenLabs, OpenAI and more

A new, open source text-to-speech model called Dia has arrived to challenge ElevenLabs, OpenAI and more

With a focus on expressive quality, reproducibility, and open access, Dia adds a distinctive new voice to the landscape of text-to-speech.

A New, Open Source Text-To-Speech Model Called Dia Has Arrived To Challenge ElevenLabs, OpenAI and More

VentureBeat made with Midjourney 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 its creators claims it surpasses the performance of competing proprietary offerings from the likes of ElevenLabs, Google’s hit NotebookLM AI podcast generation product………Continue reading…. By: Carl Franzen Source: Ventu…

Do you imagine being able to write a script and having artificial intelligence interpret it with the naturalness of a chat between friends? That’s just what Dia proposes, a text-to-voice model (TTS) that is giving you what to talk about in the technological community. It’s not a development of Google, OpenAI or ElevenLabs, but of a tiny startup, Nari Labs, made up of only two people... but with great ideas. What is Dia and what makes it special?…

In the landscape full of generative artificial intelligences, the field of voice synthesis is experiencing a particular effervescence. While established actors like ElevenLabs dominate an expanding market, attracting hundreds of millions of venture capital, a surprising initiative is emerging. Two South Korean students, without any prior in-depth expertise in AI, have developed and rendered ... Read more The article Here is Dia: the open source …

Open-Source TTS Reaches New Heights: Nari Labs Releases Dia, a 1.6B Parameter Model for Real-Time Voice Cloning and Expressive Speech Synthesis on Consumer Device

The development of text-to-speech (TTS) systems has seen significant advancements in recent years, particularly with the rise of large-scale neural models. Yet, most high-fidelity systems remain locked behind proprietary APIs and commercial platforms. Addressing this gap, Nari Labs has released Dia, a 1.6 billion parameter TTS model under the Apache 2.0 license, providing a strong open-source alternative to closed systems such as ElevenLabs and …