Launched this week
Hold a shortcut and dictate into any Mac app without sending audio to the cloud. Zen Whisper keeps core speech recognition on-device, with local models, searchable transcripts, voice memos, media transcription, and Pro tools for larger models and translation.
On-device is the right call here — I've tried a couple cloud dictation tools and the round-trip latency makes them unusable for anything longer than a quick note. Does accuracy hold up for technical vocabulary / code-adjacent terms, or is it tuned more for plain prose?
honestly love that the shortcuts work system-wide without sending audio anywhere, that on-device approach feels rare these days. nice work on keeping the core stuff local.
Zen Whisper
@okandg58 Thank you, Okan. That means a lot. We felt too many tools were making users trade away privacy just to get convenience, so we wanted to keep the core experience local while still making it fast and practical.
The system-wide shortcut piece was a huge part of that vision, so I’m really glad that stood out to you.
I got hit with a bunch of Wispr Flow promos this morning and clicked on one for later viewing when I saw your launch. My first question was why another and tough timing! But reading it's local changes this (assuming Wisp Flow is not). I'd rather have yours! Good luck today.
Really like this idea! How intensive is this on computer memory?