VibeVoice: A Frontier Open-Source Text-to-Speech Model
microsoft.github.io
VibeVoice: A Frontier Open-Source Text-to-Speech Model
1–10 of 177 posts
Re: VibeVoice: A Frontier Open-Source Text-to-Speech Model
#2[deleted - I'm an idiot]
Re: VibeVoice: A Frontier Open-Source Text-to-Speech Model
#3Wow. I admit that I am not a native speaker, but this looks (or rather, sounds) VERY impressive and I could mistake it for hearing two people talking.
Re: VibeVoice: A Frontier Open-Source Text-to-Speech Model
#4I'm really hoping one day there will be TTS does that does really nice British accents - I've surveyed them all deeply, none do.
Most that claim to do a British accent end up sounding like Kelsey Grammer - sort of an American accent pretending to be British.
Re: VibeVoice: A Frontier Open-Source Text-to-Speech Model
#5[deleted - I'm an idiot]
Whisper is speech-to-text. VibeVoice is text-to-speech.
Re: VibeVoice: A Frontier Open-Source Text-to-Speech Model
#6I'm really hoping one day there will be TTS does that does really nice British accents - I've surveyed them all deeply, none do. Most that claim to do a British accent end up sounding like Kelsey Grammer - sort of an American accent pretending to be British.
I'd like one that really nails Brummie.
Re: VibeVoice: A Frontier Open-Source Text-to-Speech Model
#7The Spontaneous Emotion dailog sounds like a team member venting through LLMs.
They could have skipped the singing part, it would be better if the model did not try to do that :)
Re: VibeVoice: A Frontier Open-Source Text-to-Speech Model
#8Re: VibeVoice: A Frontier Open-Source Text-to-Speech Model
#9MIT license - very nice!
Re: VibeVoice: A Frontier Open-Source Text-to-Speech Model
#10The Spontaneous Emotion dailog sounds like a team member venting through LLMs. They could have skipped the singing part, it would be better if the model did not try to do that :)
Hahahah. Thats what I thought too