Extremely misleading headline. Article says the opposite.
rpdillon 12 hours ago [-]
Yep, trash headline.
> The free version, called Subvox, doesn't read speech muscles. It reads the head-motion data AirPods already collect, then matches your jaw and head movements against words you have trained it on. The instructions suggest five words, ten times each. It has no language model and it publishes no accuracy score.
> So it won't take dictation. One critic said it "would fall apart with open vocabulary," and that sounds right to me.
justablob67 17 hours ago [-]
End of saas loading..
rbn3 17 hours ago [-]
Did you really have to ask Claude to turn a twitter thread into a blogpost instead of just linking to the thread itself?
mervikhaums 17 hours ago [-]
[dead]
mervikhaums 18 hours ago [-]
[flagged]
Rendered at 05:58:07 GMT+0000 (Coordinated Universal Time) with Vercel.
> The free version, called Subvox, doesn't read speech muscles. It reads the head-motion data AirPods already collect, then matches your jaw and head movements against words you have trained it on. The instructions suggest five words, ten times each. It has no language model and it publishes no accuracy score.
> So it won't take dictation. One critic said it "would fall apart with open vocabulary," and that sounds right to me.