☆ Yσɠƚԋσʂ ☆@lemmygrad.ml to technology@hexbear.netEnglish · 5 days agoA new, open source text-to-speech model called Dia has arrived to challenge ElevenLabs, OpenAI and moreventurebeat.comexternal-linkmessage-square4fedilinkarrow-up127arrow-down10cross-posted to: technology@lemmy.worldfosai@lemmy.worldtechnology@lemmygrad.mltechnology@lemmy.ml
arrow-up127arrow-down1external-linkA new, open source text-to-speech model called Dia has arrived to challenge ElevenLabs, OpenAI and moreventurebeat.com☆ Yσɠƚԋσʂ ☆@lemmygrad.ml to technology@hexbear.netEnglish · 5 days agomessage-square4fedilinkcross-posted to: technology@lemmy.worldfosai@lemmy.worldtechnology@lemmygrad.mltechnology@lemmy.ml
minus-squareBountifulEggnog [she/her]@hexbear.netlinkfedilinkEnglisharrow-up5·edit-25 days agohttps://yummy-fir-7a4.notion.site/dia Demo with clips. It sounds pretty good, I’m not very familiar with tts so I’m not sure what to expect. 10gb for the full sized model is very reasonable for consumer hardware though. Also really cool this is just two people that made this.
minus-square☆ Yσɠƚԋσʂ ☆@lemmygrad.mlOPlinkfedilinkEnglisharrow-up3·5 days agoYeah this is something you can easily run local.
https://yummy-fir-7a4.notion.site/dia
Demo with clips. It sounds pretty good, I’m not very familiar with tts so I’m not sure what to expect. 10gb for the full sized model is very reasonable for consumer hardware though. Also really cool this is just two people that made this.
Yeah this is something you can easily run local.