Cactus Compute Blog company blog

Whistle: Speech to Text in 16.9 MB

An open speech recognition model that runs on the same CPU engine as Needle. It transcribes seven languages, reaches the first token in 11 ms, and loads beside Needle so one binary turns a clip straight into tool calls.
Points
964
HN comments
185
Submissions
1
Cited by
0 commenters

AI & Machine LearningTools & Productivity2026

On Hacker News

SubmittedTitle on HNPointsComments
Oct 8, 2026Whistle: Speech to Text in 16.9 MB by gmays964185

Related posts from the same era