Yap
Hacker ApprovedShares rank 8 of 26 dictation apps by recommenders
Free, open-source voice dictation for macOS that runs Apple's on-device speech API with zero network calls. Critics mostly say it is still alpha.
Free, open-source voice dictation for macOS that runs Apple's on-device speech API with zero network calls. Critics mostly say it is still alpha.
20 people gave an opinion
- recommend it
- 17
- criticize it
- 3
- approval share
- 85%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 17 people recommend itNeeds 10 or more, met.
- 5.7 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Fully on-device, no network calls
“makes zero network calls, and since it's open source you can verify that nothing leaves your Mac”
Comment from 28 Jul 2026 in “Show HN: Yap – OSS on-device voice dictation for macOS with no model to download” “This project uses the on-device SpeechAnalyzer API directly and makes zero network calls”
Comment from 28 Jul 2026 in “Show HN: Yap – OSS on-device voice dictation for macOS with no model to download” “On-device speech recognition on macOS is such a game changer for privacy and speed.”
Comment from 28 Jul 2026 in “Show HN: Yap – OSS on-device voice dictation for macOS with no model to download” Uses Apple's SpeechAnalyzer API
“the only one I've seen so far that uses the new/improved speech-to-text API in MacOS 26 that outperforms the Whisper models”
Comment from 31 Aug 2026 in “Show HN: FnScribe – Open-source, offline dictation for macOS” “yap/Speechanalyzer is about 50% slower than fluidaudio on M1. yap interface is nicer though.”
Comment from 13 Jul 2026 in “Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor” “This project uses the on-device SpeechAnalyzer API directly and makes zero network calls”
Comment from 28 Jul 2026 in “Show HN: Yap – OSS on-device voice dictation for macOS with no model to download” Nice interface, impressive results
“yap/Speechanalyzer is about 50% slower than fluidaudio on M1. yap interface is nicer though.”
Comment from 13 Jul 2026 in “Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor” “Amazing! This is something I wanted to look into too.”
Comment from 28 Jul 2026 in “Show HN: Yap – OSS on-device voice dictation for macOS with no model to download” “I tried it and was pretty impressed.”
Comment from 9 Jun 2026 in “Siri AI”
What people warn about
Each mark is one comment
Looks AI-generated, Claude-authored code
“Last commit authored by Claude and Claude desktop... Well this is no longer of interest for me!”
Comment from 28 Jun 2026 in “Yap – free offline voice dictation for Mac/Windows/Linux (Wispr Flow alt)” “this looks like yet another AI generated whisper wrapper”
Comment from 28 Jun 2026 in “Yap – free offline voice dictation for Mac/Windows/Linux (Wispr Flow alt)” Concern about input being logged
“I don't want my input to be logged at all. It has no utility.”
Comment from 28 Jul 2026 in “Show HN: Yap – OSS on-device voice dictation for macOS with no model to download” “I believe input should be ephemeral and not logged.”
Comment from 28 Jul 2026 in “Show HN: Yap – OSS on-device voice dictation for macOS with no model to download”
Other dictation apps people recommend
The four most recommended other dictation apps, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Handy | 150 | 20 | 88% | 12 | 1 mo5 owners | Approved |
| Wispr Flow | 52 | 33 | 61% | 12 | — | — |
| MacWhisper | 31 | 9 | 78% | 12 | — | Approved |
| macOS Dictation | 26 | 44 | 37% | 10 | — | — |
| YapThis page | 17 | 3 | 85% | 5 | — | Approved |
What people said
20 of the 23 comments that mention it, newest first. Each links to the original comment.
“the only one I've seen so far that uses the new/improved speech-to-text API in MacOS 26 that outperforms the Whisper models”
“Great, hope to see the language picker soon!”
“makes zero network calls, and since it's open source you can verify that nothing leaves your Mac”
“Pretty cool. Added to this awesome-style GitHub repo I maintain containing all the best open-source voice typing tools”
“I don't want my input to be logged at all. It has no utility.”
“nothing happens after I finish speaking. No input is transcribed or pasted”
“I believe input should be ephemeral and not logged.”
“It works, on my Mac book pro.”
“On-device speech recognition on macOS is such a game changer for privacy and speed.”
“Amazing! This is something I wanted to look into too.”
“This project uses the on-device SpeechAnalyzer API directly and makes zero network calls”
“i'd be happy to switch to yours if you add parakeet support”
“how is this different from just using the built in Mac OS dictation feature?”
“The brew install path in the readme doesn't seem to work”
“yap/Speechanalyzer is about 50% slower than fluidaudio on M1. yap interface is nicer though.”
“Last commit authored by Claude and Claude desktop... Well this is no longer of interest for me!”
“this looks like yet another AI generated whisper wrapper”
“I tried it and was pretty impressed.”
“If you don't feel like downloading a large model, you can also use `yap dictate`.”
“it's definitely still very alpha”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.