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
venturebeat.com 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.
2
comments
Some preemptive advice if you're in the market of integrating TTS for some customer or service:
Do not ever use any "humanisation" tweaks. Having a computer voice stumble on a word or fucking cough is uncanny valley and how to make people feel manipulated in one simple trick.
Just don't. Everybody hates it.
As a screen reader user, I welcome new open source text to speech models.