News for hackers. Stuff that matters.
Re:Microsoft VibeVoice: Open-Source Frontier Voice AI by gagan2020 on Tuesday April 28, 2026 @11:05AM (#47935668)
It is not good for text to speech (TTS) as well. I am trying it for few days. First of all 1.5B model documentation is not there. 0.5B realtime is shit model. I was converting text, line by line and it was randomly adding music and couldn't handle special characters like "…".

I really disappointed with this model to say the least.

Re:Microsoft VibeVoice: Open-Source Frontier Voice AI by Stagnant on Tuesday April 28, 2026 @02:40PM (#47938628)
The 7B parameter Vibevoice TTS model is still the most impressive local TTS model i've tried. It was pulled by Microsoft a few days after its release due to "abuse potential" but it can be found in various community maintained huggingface repos.
Re:Microsoft VibeVoice: Open-Source Frontier Voice AI by tjungblut on Tuesday April 28, 2026 @03:19PM (#47939255)
yep, it seems this was trained on large amount of podcasts with ad jingles or phone call queues with elevator music. I was also pretty disappointed to run the TTS last week.
Re:Microsoft VibeVoice: Open-Source Frontier Voice AI by SyneRyder on Thursday April 30, 2026 @10:50AM (#47963428)
> ...it was randomly adding music...

I've been noticing this with the Mistral Voxtral TTS models too. I have my AI record a morning briefing podcast for myself, and occasionally there are sounds like music at the start (the british voice had a musical tone underneath that sounded a little like the end of the BBC News theme). I don't think I've ever encountered that with the OpenAI TTS models, so they're now my default go-to again.