{"slug": "yap", "name": "yap", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 5, "commenters": 9, "warners": 2, "score": 1.951, "rising": -0.31, "first": "2026-04-06", "latest": "2026-08-31", "why": "If you want to use this on the CLI: https://github.com/finnvoor/yap.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 5, "neutral": 2, "compare": 1, "warn": 2}, "spark": [0, 0, 0, 0, 0, 1, 0, 1, 2, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "If you want to use this on the CLI: https://github.com/finnvoor/yap.", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/finnvoor/yap", "official_url": "https://github.com/finnvoor/yap", "pricing": "", "aliases": ["yap", "Yap"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 792249393, "item_id": 49515587, "url": "https://news.ycombinator.com/item?id=49515587", "by": "dfltr", "date": "2026-08-31", "stance": "recommend", "quote": "which is 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.", "excerpt": "Or https://github.com/FrigadeHQ/yap which is 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. I expect most dictation software is going to start supporting the local API pretty soon, it's free real estate.", "context": "", "use_case": "Speech-to-text using macOS 26 API", "switched_from": "", "story": "Show HN: FnScribe \u2013 Open-source, offline dictation for macOS"}, {"id": 785307553, "item_id": 49081722, "url": "https://news.ycombinator.com/item?id=49081722", "by": "primaprashant", "date": "2026-07-28", "stance": "recommend", "quote": "Pretty cool. Added to this awesome-style GitHub repo I maintain", "excerpt": "Pretty cool. Added to this awesome-style GitHub repo I maintain containing all the best open-source voice typing tools: https://github.com/primaprashant/awesome-voice-typing", "context": "", "use_case": "voice dictation", "switched_from": "", "story": "Show HN: Yap \u2013 OSS on-device voice dictation for macOS with no model to download"}, {"id": 782359136, "item_id": 48897446, "url": "https://news.ycombinator.com/item?id=48897446", "by": "foobarqux", "date": "2026-07-13", "stance": "recommend", "quote": "If you want to use this on the CLI: https://github.com/finnvoor/yap.", "excerpt": "If you want to use this on the CLI: https://github.com/finnvoor/yap. Supports SRT/TXT/VTT or JSON-with-optional-word-level-timestamps output and progress meter. Also it can transcribe live system audio.", "context": "", "use_case": "CLI transcription", "switched_from": "", "story": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor"}, {"id": 782357520, "item_id": 48897345, "url": "https://news.ycombinator.com/item?id=48897345", "by": "foobarqux", "date": "2026-07-13", "stance": "recommend", "quote": "yap interface is nicer though.", "excerpt": "Just tried test using yap on a single ~1hr mp3: yap/Speechanalyzer is about 50% slower than fluidaudio on M1. yap interface is nicer though. https://github.com/finnvoor/yap", "context": "", "use_case": "speech-to-text CLI", "switched_from": "", "story": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor"}, {"id": 775275120, "item_id": 48454695, "url": "https://news.ycombinator.com/item?id=48454695", "by": "hbn", "date": "2026-06-08", "stance": "recommend", "quote": "Someone made a cli utility to play with it: https://github.com/finnvoor/yap", "excerpt": "They actually released a pretty good dictation model in the OS 26 updates. Someone made a cli utility to play with it: https://github.com/finnvoor/yap I tried it and was pretty impressed. That said I haven't heard anything yet about them switching to this for the text input voice dictation in iOS but it would be really nice.", "context": "", "use_case": "Speech-to-text dictation CLI", "switched_from": "", "story": "Siri AI"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 785262000, "item_id": 49078875, "url": "https://news.ycombinator.com/item?id=49078875", "by": "__erik", "date": "2026-07-27", "stance": "warn", "quote": "The brew install path in the readme doesn't seem to work", "excerpt": "This is super cool! The brew install path in the readme doesn't seem to work remote: Repository not found. fatal: repository 'https://github.com/frigadehq/homebrew-tap/' not found", "context": "", "use_case": "voice dictation", "switched_from": "", "story": "Show HN: Yap \u2013 OSS on-device voice dictation for macOS with no model to download"}, {"id": 779296674, "item_id": 48706042, "url": "https://news.ycombinator.com/item?id=48706042", "by": "taffydavid", "date": "2026-06-28", "stance": "warn", "quote": "this looks like yet another AI generated whisper wrapper", "excerpt": "I love on-device transcription apps, but this looks like yet another AI generated whisper wrapper. I'm put off by the readme which is clearly LLM generated, with emdash all over the place and bits that smell of user questions turned into talking points. > Why not the Fn / key? It's the obvious one-finger choice, but on macOS the Fn key emits no real keypress \u2014 only a hidden hardware flag \u2014 so And > macOS permissions ", "context": "", "use_case": "voice dictation", "switched_from": "", "story": "Yap \u2013 free offline voice dictation for Mac/Windows/Linux (Wispr Flow alt)"}]}], "who": [], "tags": [], "use_cases": ["voice dictation", "speech-to-text using macos 26 api", "transcription cli", "speech to text", "on-device voice dictation", "cli transcription"], "compared": [{"slug": "handy", "name": "Handy", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "whisper", "name": "Whisper", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "nvidia-parakeet", "name": "NVIDIA Parakeet", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 748428336, "item_id": 46776771, "url": "https://news.ycombinator.com/item?id=46776771", "by": "ChadNauseam", "date": "2026-01-26", "stance": "recommend", "quote": "working on this since approximately when claude code was first released", "excerpt": "I\u2019ve been working on this since approximately when claude code was first released: https://github.com/yaptown/yap As hobby projects go it\u2019s \u201cin production\u201d with maybe 50 active users, so nothing crazy. Definitely less ambitious than a sqlite successor. But it\u2019s not trivial. (The repo history is truncated to save money on github LFS storage.)", "context": "", "use_case": "", "switched_from": "", "story": "Any application that can be written in a system language, eventually will be"}, {"id": 744481601, "item_id": 46530100, "url": "https://news.ycombinator.com/item?id=46530100", "by": "ChadNauseam", "date": "2026-01-07", "stance": "recommend", "quote": "My hope is just for my app to be a useful supplement.", "excerpt": "Haha, thanks for checking it out! I really appreciate the feedback. > First thing I got was \u201cbrowser not supported\u201d on mobile. Yeah, I use some APIs that were only implemented in Safari on iOS 26. Kind of annoying but I use Android so I didn't realize until too late. I should fix it, but it's not a priority given the numerous other things that need improvement (as you noticed!) > The voices in Portuguese are particul", "context": "", "use_case": "language learning", "switched_from": "", "story": "The creator of Claude Code's Claude setup"}], "threads": [{"url": "https://news.ycombinator.com/item?id=49073834", "title": "Show HN: Yap \u2013 OSS on-device voice dictation for macOS with no model to download", "mentions": 6}, {"url": "https://news.ycombinator.com/item?id=48894752", "title": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49475159", "title": "Show HN: FnScribe \u2013 Open-source, offline dictation for macOS", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48703848", "title": "Yap \u2013 free offline voice dictation for Mac/Windows/Linux (Wispr Flow alt)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48449084", "title": "Siri AI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47666024", "title": "Show HN: Ghost Pepper \u2013 100% local hold-to-talk speech-to-text for macOS", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"recommend": 1}, "2026-05": {}, "2026-06": {"recommend": 1, "warn": 1}, "2026-07": {"recommend": 2, "warn": 1, "compare": 1, "neutral": 2}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 792249393, "item_id": 49515587, "url": "https://news.ycombinator.com/item?id=49515587", "by": "dfltr", "date": "2026-08-31", "stance": "recommend", "quote": "which is 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.", "excerpt": "Or https://github.com/FrigadeHQ/yap which is 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. I expect most dictation software is going to start supporting the local API pretty soon, it's free real estate.", "context": "", "use_case": "Speech-to-text using macOS 26 API", "switched_from": "", "story": "Show HN: FnScribe \u2013 Open-source, offline dictation for macOS"}, {"id": 785608080, "item_id": 49100505, "url": "https://news.ycombinator.com/item?id=49100505", "by": "foobarqux", "date": "2026-07-29", "stance": "neutral", "quote": "There is a pre-existing transcription CLI app with the same name.", "excerpt": "There is a pre-existing transcription CLI app with the same name. https://github.com/finnvoor/yap", "context": "", "use_case": "transcription CLI", "switched_from": "", "story": "Show HN: Yap \u2013 OSS on-device voice dictation for macOS with no model to download"}, {"id": 785307553, "item_id": 49081722, "url": "https://news.ycombinator.com/item?id=49081722", "by": "primaprashant", "date": "2026-07-28", "stance": "recommend", "quote": "Pretty cool. Added to this awesome-style GitHub repo I maintain", "excerpt": "Pretty cool. Added to this awesome-style GitHub repo I maintain containing all the best open-source voice typing tools: https://github.com/primaprashant/awesome-voice-typing", "context": "", "use_case": "voice dictation", "switched_from": "", "story": "Show HN: Yap \u2013 OSS on-device voice dictation for macOS with no model to download"}, {"id": 785274192, "item_id": 49079637, "url": "https://news.ycombinator.com/item?id=49079637", "by": "hbn", "date": "2026-07-27", "stance": "neutral", "quote": "an app layer for the new speech to text APIs introduced in OS 26", "excerpt": "I thought I was familiar with this project but I think it\u2019s unrelated to this one I remembered from last year? Same name and also more or less an app layer for the new speech to text APIs introduced in OS 26. https://github.com/finnvoor/yap", "context": "", "use_case": "speech to text", "switched_from": "", "story": "Show HN: Yap \u2013 OSS on-device voice dictation for macOS with no model to download"}, {"id": 785270160, "item_id": 49079385, "url": "https://news.ycombinator.com/item?id=49079385", "by": "pancomplex", "date": "2026-07-27", "stance": "neutral", "quote": "That would be a super trivial fork actually!", "excerpt": "That would be a super trivial fork actually! You basically just need this file https://github.com/FrigadeHQ/yap/blob/main/Sources/Services/AudioCaptureService.swift and then wrap a cli around it :)", "context": "", "use_case": "on-device voice dictation", "switched_from": "", "story": "Show HN: Yap \u2013 OSS on-device voice dictation for macOS with no model to download"}, {"id": 785262626, "item_id": 49078914, "url": "https://news.ycombinator.com/item?id=49078914", "by": "eric_khun", "date": "2026-07-27", "stance": "compare", "quote": "i'd be happy to switch to yours if you add parakeet support", "excerpt": "link to the benchmark against parakeet TDT v2 (the one im using now with spokenly) : https://get-inscribe.com/blog/parakeet-moss-apple-speech-benchmark.html NVIDIA Parakeet TDT v2 still best, but look like apple is not far behind. i'd be happy to switch to yours if you add parakeet support, but that ight defy the purpose of the repo", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Yap \u2013 OSS on-device voice dictation for macOS with no model to download"}, {"id": 785262000, "item_id": 49078875, "url": "https://news.ycombinator.com/item?id=49078875", "by": "__erik", "date": "2026-07-27", "stance": "warn", "quote": "The brew install path in the readme doesn't seem to work", "excerpt": "This is super cool! The brew install path in the readme doesn't seem to work remote: Repository not found. fatal: repository 'https://github.com/frigadehq/homebrew-tap/' not found", "context": "", "use_case": "voice dictation", "switched_from": "", "story": "Show HN: Yap \u2013 OSS on-device voice dictation for macOS with no model to download"}, {"id": 782359136, "item_id": 48897446, "url": "https://news.ycombinator.com/item?id=48897446", "by": "foobarqux", "date": "2026-07-13", "stance": "recommend", "quote": "If you want to use this on the CLI: https://github.com/finnvoor/yap.", "excerpt": "If you want to use this on the CLI: https://github.com/finnvoor/yap. Supports SRT/TXT/VTT or JSON-with-optional-word-level-timestamps output and progress meter. Also it can transcribe live system audio.", "context": "", "use_case": "CLI transcription", "switched_from": "", "story": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor"}, {"id": 782357520, "item_id": 48897345, "url": "https://news.ycombinator.com/item?id=48897345", "by": "foobarqux", "date": "2026-07-13", "stance": "recommend", "quote": "yap interface is nicer though.", "excerpt": "Just tried test using yap on a single ~1hr mp3: yap/Speechanalyzer is about 50% slower than fluidaudio on M1. yap interface is nicer though. https://github.com/finnvoor/yap", "context": "", "use_case": "speech-to-text CLI", "switched_from": "", "story": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor"}, {"id": 779296674, "item_id": 48706042, "url": "https://news.ycombinator.com/item?id=48706042", "by": "taffydavid", "date": "2026-06-28", "stance": "warn", "quote": "this looks like yet another AI generated whisper wrapper", "excerpt": "I love on-device transcription apps, but this looks like yet another AI generated whisper wrapper. I'm put off by the readme which is clearly LLM generated, with emdash all over the place and bits that smell of user questions turned into talking points. > Why not the Fn / key? It's the obvious one-finger choice, but on macOS the Fn key emits no real keypress \u2014 only a hidden hardware flag \u2014 so And > macOS permissions ", "context": "", "use_case": "voice dictation", "switched_from": "", "story": "Yap \u2013 free offline voice dictation for Mac/Windows/Linux (Wispr Flow alt)"}, {"id": 775275120, "item_id": 48454695, "url": "https://news.ycombinator.com/item?id=48454695", "by": "hbn", "date": "2026-06-08", "stance": "recommend", "quote": "Someone made a cli utility to play with it: https://github.com/finnvoor/yap", "excerpt": "They actually released a pretty good dictation model in the OS 26 updates. Someone made a cli utility to play with it: https://github.com/finnvoor/yap I tried it and was pretty impressed. That said I haven't heard anything yet about them switching to this for the text input voice dictation in iOS but it would be really nice.", "context": "", "use_case": "Speech-to-text dictation CLI", "switched_from": "", "story": "Siri AI"}, {"id": 762668080, "item_id": 47666755, "url": "https://news.ycombinator.com/item?id=47666755", "by": "mathis", "date": "2026-04-06", "stance": "recommend", "quote": "you can also use `yap dictate`", "excerpt": "If you don't feel like downloading a large model, you can also use `yap dictate`. Yap leverages the built-in models exposed though Speech.framework on macOS 26 (Tahoe). Project repo: https://github.com/finnvoor/yap", "context": "", "use_case": "Dictation via macOS speech models", "switched_from": "", "story": "Show HN: Ghost Pepper \u2013 100% local hold-to-talk speech-to-text for macOS"}]}