A new, open source text-to-speech model called Dia has arrived to challenge ElevenLabs, OpenAI and more (venturebeat.com)
from cm0002@lemmy.world to technology@lemmy.world on 23 Apr 15:02
https://lemmy.world/post/28609014

#technology

threaded - newest

whaleross@lemmy.world on 23 Apr 18:30 next collapse

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.

shortwavesurfer@lemmy.zip on 23 Apr 18:31 collapse

As a screen reader user, I welcome new open source text to speech models.