{"slug": "whisper-cpp", "name": "whisper.cpp", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 6, "commenters": 11, "warners": 0, "score": 6.012, "rising": -1.96, "first": "2025-11-14", "latest": "2026-07-18", "why": "Whisper.cpp has been pretty solid for me if you want something free and local.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 2, "compare": 3, "warn": 0}, "spark": [1, 3, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Whisper.cpp has been pretty solid for me if you want something free and local.", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/ggml-org/whisper.cpp", "official_url": "https://github.com/ggml-org/whisper.cpp", "pricing": "", "aliases": ["whisper.cpp", "Whisper.cpp"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 772407504, "item_id": 48275469, "url": "https://news.ycombinator.com/item?id=48275469", "by": "yashnitro", "date": "2026-05-25", "version": null, "stance": "recommend", "quote": "Whisper.cpp has been pretty solid for me if you want something free and local.", "excerpt": "Whisper.cpp has been pretty solid for me if you want something free and local.", "context": "", "use_case": "local speech-to-text", "switched_from": "", "story": "Ask HN: Best Free Local STT?"}, {"id": 751319427, "item_id": 46957464, "url": "https://news.ycombinator.com/item?id=46957464", "by": "mythz", "date": "2026-02-10", "version": null, "stance": "recommend", "quote": "followed by Whisper.cpp", "excerpt": "Big fan of Salvatore's voxtral.c and flux2.c projects - hope they continue to get optimized as it'd be great to have lean options without external deps. Unfortunately it's currently too slow for real-world use (AMD 7800X3D/Blas) when adding Voice Input support to llms-py [1]. In the end Omarchy's new support for voxtype.io provided the nicest UX, followed by Whisper.cpp, and despite being slower, OpenAI's Whisper is ", "context": "", "use_case": "", "switched_from": "", "story": "Pure C, CPU-only inference with Mistral Voxtral Realtime 4B speech to text model"}, {"id": 740266546, "item_id": 46266659, "url": "https://news.ycombinator.com/item?id=46266659", "by": "blazingbanana", "date": "2025-12-14", "version": null, "stance": "recommend", "quote": "for making this even possible.", "excerpt": "https://play.google.com/store/apps/details?id=com.blazingbanana.whistle Completely free, no ads, no in-app purchases and no accounts / network required offline voice transcription. I have also built the macOS/Windows/Linux versions which I'll also make free to download and available on my site soon (https://blazingbanana.com/). iOS version is built and works (extremely well), just waiting for the Apple Developer sign", "context": "", "use_case": "Offline Whisper inference", "switched_from": "", "story": "Ask HN: What Are You Working On? (December 2025)"}, {"id": 739560928, "item_id": 46222558, "url": "https://news.ycombinator.com/item?id=46222558", "by": "mobilio", "date": "2025-12-10", "version": null, "stance": "recommend", "quote": "Yes - there is a way: https://github.com/ggml-org/whisper.cpp", "excerpt": "Yes - there is a way: https://github.com/ggml-org/whisper.cpp", "context": "", "use_case": "", "switched_from": "", "story": "Qwen3-Omni-Flash-2025-12-01\uff1aa next-generation native multimodal large model"}, {"id": 738171856, "item_id": 46135741, "url": "https://news.ycombinator.com/item?id=46135741", "by": "hombre_fatal", "date": "2025-12-03", "version": null, "stance": "recommend", "quote": "I vibe-coded a whisper.cpp setup where I hold super+semicolon, speak, and release", "excerpt": "Funny you say that. Last month I vibe-coded a whisper.cpp setup where I hold super+semicolon, speak, and release, and then it injects a transcription of what I said into whatever has focus. The only reason I looked at the code was curiosity and to impart some aesthetic preferences on it. Before it, I was using https://wisprflow.ai/ for ez transcription since I would never have had the energy to build it myself nor wo", "context": "", "use_case": "Voice dictation", "switched_from": "", "story": "Garry Tan claims Zoho will be out of business due to vibe coding"}]}], "caveats": [], "who": [{"by": "jspizziri", "context": "runs an audiobook side project", "url": "https://news.ycombinator.com/item?id=46314502", "date": "2025-12-18"}, {"by": "lxe", "context": "Linux user", "url": "https://news.ycombinator.com/item?id=45932611", "date": "2025-11-14"}], "tags": [], "use_cases": ["local speech-to-text", "speech recognition", "speech transcription", "transcribing narration for proofing", "offline whisper inference", "voice dictation"], "compared": [{"slug": "wispr-flow", "name": "Wispr Flow", "co": 1, "switched_from": 0, "switched_to": 1}, {"slug": "whisper", "name": "Whisper", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 762724976, "item_id": 47670311, "url": "https://news.ycombinator.com/item?id=47670311", "by": "pdyc", "date": "2026-04-06", "version": null, "stance": "recommend", "quote": "Now its my daily driver", "excerpt": "interesting, i wanted something like this but i am on linux so i modified whisper example to run on cli. Its quite basic, uses ctrl+alt+s to start/stop, when you stop it copies text to clipboard that's it. Now its my daily driver https://github.com/newbeelearn/whisper.cpp", "context": "Linux user", "use_case": "speech-to-text on Linux", "switched_from": "", "story": "Show HN: Ghost Pepper \u2013 100% local hold-to-talk speech-to-text for macOS"}], "threads": [{"url": "https://news.ycombinator.com/item?id=46954049", "title": "Pure C, CPU-only inference with Mistral Voxtral Realtime 4B speech to text model", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=45930659", "title": "Show HN: Chirp \u2013 Local Windows dictation with ParakeetV3 no executable required", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48911793", "title": "Speech Recognition and TTS in less than 500kb", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48275395", "title": "Ask HN: Best Free Local STT?", "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}, {"url": "https://news.ycombinator.com/item?id=46731068", "title": "Ask HN: What's the current best local/open speech-to-speech setup?", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {"recommend": 3, "neutral": 1}, "2026-01": {"compare": 1, "neutral": 1}, "2026-02": {"compare": 1, "recommend": 1}, "2026-03": {}, "2026-04": {}, "2026-05": {"recommend": 1}, "2026-06": {}, "2026-07": {"compare": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 783438032, "item_id": 48964877, "url": "https://news.ycombinator.com/item?id=48964877", "by": "1vuio0pswjnm7", "date": "2026-07-18", "version": null, "stance": "compare", "quote": "Compare", "excerpt": "Compare https://github.com/ggml-org/whisper.cpp/", "context": "", "use_case": "speech recognition", "switched_from": "", "story": "Speech Recognition and TTS in less than 500kb"}, {"id": 772407504, "item_id": 48275469, "url": "https://news.ycombinator.com/item?id=48275469", "by": "yashnitro", "date": "2026-05-25", "version": null, "stance": "recommend", "quote": "Whisper.cpp has been pretty solid for me if you want something free and local.", "excerpt": "Whisper.cpp has been pretty solid for me if you want something free and local.", "context": "", "use_case": "local speech-to-text", "switched_from": "", "story": "Ask HN: Best Free Local STT?"}, {"id": 751319427, "item_id": 46957464, "url": "https://news.ycombinator.com/item?id=46957464", "by": "mythz", "date": "2026-02-10", "version": null, "stance": "recommend", "quote": "followed by Whisper.cpp", "excerpt": "Big fan of Salvatore's voxtral.c and flux2.c projects - hope they continue to get optimized as it'd be great to have lean options without external deps. Unfortunately it's currently too slow for real-world use (AMD 7800X3D/Blas) when adding Voice Input support to llms-py [1]. In the end Omarchy's new support for voxtype.io provided the nicest UX, followed by Whisper.cpp, and despite being slower, OpenAI's Whisper is ", "context": "", "use_case": "", "switched_from": "", "story": "Pure C, CPU-only inference with Mistral Voxtral Realtime 4B speech to text model"}, {"id": 751281553, "item_id": 46955097, "url": "https://news.ycombinator.com/item?id=46955097", "by": "Curiositry", "date": "2026-02-09", "version": null, "stance": "compare", "quote": "ala Whisper.cpp stream or Moonshine", "excerpt": "This was a breeze to install on Linux. However, I haven't managed to get realtime transcription working yet, ala Whisper.cpp stream or Moonshine. --from-mic only supports Mac. I'm able to capture audio with ffmpeg, but adapting the ffmpeg example to use mic capture hasn't worked yet: ffmpeg -f pulse -channels 1 -i 1 -f s16le - 2>/dev/null | ./voxtral -d voxtral-model --stdin It's possible my system is simply under sp", "context": "", "use_case": "", "switched_from": "", "story": "Pure C, CPU-only inference with Mistral Voxtral Realtime 4B speech to text model"}, {"id": 747832993, "item_id": 46739562, "url": "https://news.ycombinator.com/item?id=46739562", "by": "BiraIgnacio", "date": "2026-01-23", "version": null, "stance": "neutral", "quote": "I'll probably go with whisper (with whisper.cpp)", "excerpt": "oh I've been looking into whisper and vosk in the last few days. I'll probably go with whisper (with whisper.cpp) but has anyone compared it to vosk models?", "context": "", "use_case": "local speech-to-text", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 744940850, "item_id": 46558803, "url": "https://news.ycombinator.com/item?id=46558803", "by": "satvikpendem", "date": "2026-01-09", "version": null, "stance": "compare", "quote": "yet it completes in a fraction of the time using batching", "excerpt": "Batching is essentially running multiple instances at once, ie bundling 8 segments and running them simultaneously on the processing unit, but which obviously takes more RAM to do. Notice, however, that if you drop the precision to int8 from fp16, you use basically the same amount of RAM as whisper.cpp yet it completes in a fraction of the time using batching [0]. Yes, if you check their community integrations sectio", "context": "", "use_case": "speech transcription", "switched_from": "", "story": "Dell's CES 2026 chat was the most pleasingly un-AI briefing I've had in 5 years"}, {"id": 741032033, "item_id": 46314502, "url": "https://news.ycombinator.com/item?id=46314502", "by": "jspizziri", "date": "2025-12-18", "version": null, "stance": "neutral", "quote": "I use whisper.cpp to transcribe them and then git and a few other scripts to compare the transcript with the actual book text.", "excerpt": "There's a really awesome site called Librivox [1], where volunteers narrate books that are in the public domain. Those recordings are also in the public domain as well (this is just part of the Librivox thing). The quality of those recordings (both the narration, and the actual recording quality) varies quite a bit and most of them aren't at a quality I'd expect people to pay for and thus aren't useable for me. I've ", "context": "runs an audiobook side project", "use_case": "transcribing narration for proofing", "switched_from": "", "story": "Ask HN: Those making $500/month on side projects in 2025 \u2013 Show and tell"}, {"id": 740266546, "item_id": 46266659, "url": "https://news.ycombinator.com/item?id=46266659", "by": "blazingbanana", "date": "2025-12-14", "version": null, "stance": "recommend", "quote": "for making this even possible.", "excerpt": "https://play.google.com/store/apps/details?id=com.blazingbanana.whistle Completely free, no ads, no in-app purchases and no accounts / network required offline voice transcription. I have also built the macOS/Windows/Linux versions which I'll also make free to download and available on my site soon (https://blazingbanana.com/). iOS version is built and works (extremely well), just waiting for the Apple Developer sign", "context": "", "use_case": "Offline Whisper inference", "switched_from": "", "story": "Ask HN: What Are You Working On? (December 2025)"}, {"id": 739560928, "item_id": 46222558, "url": "https://news.ycombinator.com/item?id=46222558", "by": "mobilio", "date": "2025-12-10", "version": null, "stance": "recommend", "quote": "Yes - there is a way: https://github.com/ggml-org/whisper.cpp", "excerpt": "Yes - there is a way: https://github.com/ggml-org/whisper.cpp", "context": "", "use_case": "", "switched_from": "", "story": "Qwen3-Omni-Flash-2025-12-01\uff1aa next-generation native multimodal large model"}, {"id": 738171856, "item_id": 46135741, "url": "https://news.ycombinator.com/item?id=46135741", "by": "hombre_fatal", "date": "2025-12-03", "version": null, "stance": "recommend", "quote": "I vibe-coded a whisper.cpp setup where I hold super+semicolon, speak, and release", "excerpt": "Funny you say that. Last month I vibe-coded a whisper.cpp setup where I hold super+semicolon, speak, and release, and then it injects a transcription of what I said into whatever has focus. The only reason I looked at the code was curiosity and to impart some aesthetic preferences on it. Before it, I was using https://wisprflow.ai/ for ez transcription since I would never have had the energy to build it myself nor wo", "context": "", "use_case": "Voice dictation", "switched_from": "", "story": "Garry Tan claims Zoho will be out of business due to vibe coding"}, {"id": 734921776, "item_id": 45932611, "url": "https://news.ycombinator.com/item?id=45932611", "by": "lxe", "date": "2025-11-14", "version": null, "stance": "recommend", "quote": "I use it for Linux using whisper CPP and it works great", "excerpt": "https://github.com/lxe/yapyap/tree/parakeet-nemo It's been a while, so I don't know if it's going to work because of the Nemo toolkit ASR numpy dependency issues. I use it for Linux using whisper CPP and it works great", "context": "Linux user", "use_case": "local dictation on Linux", "switched_from": "", "story": "Show HN: Chirp \u2013 Local Windows dictation with ParakeetV3 no executable required"}, {"id": 734901826, "item_id": 45931364, "url": "https://news.ycombinator.com/item?id=45931364", "by": "lxe", "date": "2025-11-14", "version": null, "stance": "recommend", "quote": "I'm using Whisper.CPP with CUDA acceleration.", "excerpt": "I've done something similar for Linux and Mac. I originally used Whisper and then switched to Parakeet. I much prefer whisper after playing with both. Maybe I'm not configuring Parakeet correctly, But the transcription that comes out of Whisper is usually pretty much spot on. It automatically removes all the \"ooms\" and all the \"ahs\" and it's just way more natural, in my opinion. I'm using Whisper.CPP with CUDA accele", "context": "built dictation tools for Linux and Mac", "use_case": "local dictation with CUDA", "switched_from": "", "story": "Show HN: Chirp \u2013 Local Windows dictation with ParakeetV3 no executable required"}]}