bazlan

Show HN: Vui – open-source voice mode

Posted by bazlan on Monday June 08, 2026 @07:40AM
from the show-hn dept.

An open source voice mode stack that runs on a single consumer gpu

( Read More... | no comments | on HN )

Posted by bazlan on Wednesday June 03, 2026 @07:10PM
from the twitter.com dept.

( Read More... | no comments | on HN )

Re:VUI – open-source Jarvis stack with a 300M TTS Model on Friday May 15, 2026 @08:20AM (#48147709)

What's the buisness?

Re:VUI – open-source Jarvis stack with a 300M TTS Model on Friday May 15, 2026 @08:20AM (#48147707)

thanks!

Re:VUI – open-source Jarvis stack with a 300M TTS Model on Friday May 15, 2026 @08:20AM (#48147705)

Haha yeah this is the idea

Re:VUI – open-source Jarvis stack with a 300M TTS Model on Friday May 15, 2026 @08:20AM (#48147703)

Definitely possible but tricky with stacks > 1B in params

Posted by bazlan on Thursday May 14, 2026 @10:56AM
from the twitter.com dept.

( Read More... | 9 comments | 8 points | on HN )

Re:Microsoft VibeVoice: A Frontier Open-Source Text-to-Speech Model on Wednesday September 03, 2025 @02:03PM (#45118740)

Sad to not see vui on the comparisons!

A 100M podcast model

Posted by bazlan on Sunday June 08, 2025 @08:28AM
from the twitter.com dept.

( Read More... | 5 comments | 14 points | on HN )

Re:Show HN: Dia, an open-weights TTS model for generating realistic di... on Tuesday April 22, 2025 @05:00AM (#43760254)

fluxions.ai has a similar model

Re:Launch HN: Hamming (YC S24) – Automated Testing for Voice Agents on Friday August 16, 2024 @02:15AM (#41263610)

As someone who has worked in TTS for over 4 years now. I can tell you that evaluation is the most difficult aspect of generative audio ML.

How will this really check that the models are performing well vs just listening?

Re:PHP Doesn't Suck Anymore on Saturday May 04, 2024 @06:03AM (#40256344)

Let it die