Show HN: Yap – OSS on-device voice dictation for macOS with no model to download

Post by jorisw » Tue, Jul 28, 2026, 5:31 PM UTC

pancomplex wrote: post #38

jorisw wrote: post #28

Strangely, on my macOS 27 Beta build 26A5388g, nothing happens after I finish speaking. No input is transcribed or pasted and nothing is shown in the history. I do see the input being listed to — there's an audio graph animated as I speak (~US English), though it appears to be late in picking up my speech. Only my second "test?" is represented in the graph as it moves leftwards. I went through all the permissions, th…

Sorry about these issues - appreciate all the details. Are you on an Intel Mac by any chance?

Post by pancomplex » Tue, Jul 28, 2026, 6:46 PM UTC

outoftheweed wrote: post #42

built a small voice notes thing for myself last week and the surprise was that transcription accuracy wasn't the hard part. it's that i almost never want the raw transcript, i want the cleaned up version of it. keeping that out of scope is probably the right call for a dictation tool though.

Post by stevenhubertron » Wed, Jul 29, 2026, 2:11 AM UTC

Post by ganeshmshetty » Wed, Jul 29, 2026, 4:51 AM UTC

echoangle wrote: post #32

pancomplex wrote: post #13

Earlier quoted context omitted.

I think it once did! Now it doesn't - ways to easily verify this: 1) install the dmg in the GH repo 2) turn off wifi 3) use it offline

That doesn’t prove it doesn’t send data if it has the possibility. It could use the offline model only as a fallback.

Post by BurpyDave » Wed, Jul 29, 2026, 11:49 AM UTC