Open-source voice dictation for Mac, fully on-device
Yap turns speech into text anywhere you can type on your Mac. Set a hotkey, talk, press it again, and the words get pasted into whatever field you were in. It runs entirely on device using macOS 26's speech APIs, so there's no model to download and nothing leaves your machine. It's around 3,000 lines of native Swift in a 4 MB app that idles near 60 MB of memory. Free, MIT licensed, and built by Frigade because we wanted it for ourselves.
Hey Product Hunt 👋
I'm Christian, CTO at Frigade. Like everyone else, we recently switched to "Yap-based development". However, the dictation tools we tried either wanted a subscription, made us download and run beefy 1GB+ models, or shipped a whole browser engine to run a menu bar icon. Many of them also rely on sending your private transcripts to remote APIs (even Apple's built in dictation!).
How did we do this? With macOS 26, Apple shipped an on-device speech API called SpeechAnalyzer that turned out to match frontier API models in benchmarks, so we built Yap on top of it for ourselves and open sourced it.
You set a hotkey, talk, press it again, and the text lands in whatever you were typing in. It carries no model of its own and makes no network calls, and the whole thing uses just a few MB of memory.
It's free and MIT licensed. Would love your feedback, and I'm happy to get into the Speech APIs or the Swift side if you want to know what's under the hood.
About Yap on Product Hunt
“Open-source voice dictation for Mac, fully on-device”
Yap launched on Product Hunt on July 30th, 2026 and earned 148 upvotes and 21 comments, placing #10 on the daily leaderboard. Yap turns speech into text anywhere you can type on your Mac. Set a hotkey, talk, press it again, and the words get pasted into whatever field you were in. It runs entirely on device using macOS 26's speech APIs, so there's no model to download and nothing leaves your machine. It's around 3,000 lines of native Swift in a 4 MB app that idles near 60 MB of memory. Free, MIT licensed, and built by Frigade because we wanted it for ourselves.
On the analytics side, Yap competes within Productivity, Artificial Intelligence, GitHub and Menu Bar Apps — topics that collectively have 1.2M followers on Product Hunt. The dashboard above tracks how Yap performed against the three products that launched closest to it on the same day.
Who hunted Yap?
Yap was hunted by Christian Mathiesen. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Yap including community comment highlights and product details, visit the product overview.
Christian Mathiesen