Y
Hacker News
new
|
ask
|
show
|
jobs
by
CubsFan1060
48 days ago
Great post last night from Simon:
https://simonwillison.net/2026/Apr/27/vibevoice/
2 comments
542458
48 days ago
Note that this just covers the Speech-to-Text/Speech-Recognition aspect (a-la whisper), there's also models for long-form Text-To-Speech and steaming Text-To-Speech.
link
JumpCrisscross
48 days ago
“VibeVoice can only handle up to an hour of audio”
Why?
link