{"slug": "vosk", "name": "Vosk", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 3, "commenters": 7, "warners": 0, "score": 2.998, "rising": 1.67, "first": "2025-11-14", "latest": "2026-10-14", "why": "I went with Vosk because it's pretty trivial to lock input down to a set vocabulary", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 2, "compare": 2, "warn": 0}, "spark": [0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 2], "listed": true, "loved": [], "caveat": "", "short_quote": "I went with Vosk because it's pretty trivial to lock input down to a set vocabulary", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/alphacep/vosk-api", "official_url": "https://alphacephei.com/vosk/", "pricing": "", "aliases": ["Vosk"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 801316032, "item_id": 50082252, "url": "https://news.ycombinator.com/item?id=50082252", "by": "vunderba", "date": "2026-10-14", "version": null, "stance": "recommend", "quote": "I went with Vosk because it's pretty trivial to lock input down to a set vocabulary", "excerpt": "OP here - I went with Vosk because it's pretty trivial to lock input down to a set vocabulary (in this case numbers) and from my testing works relatively well on most browsers. (webkit, firefox, etc) https://github.com/alphacep/vosk-api", "context": "", "use_case": "Speech recognition for input", "switched_from": "", "story": "Show HN: How random are you?"}, {"id": 800168000, "item_id": 50010500, "url": "https://news.ycombinator.com/item?id=50010500", "by": "sfpk", "date": "2026-10-08", "version": null, "stance": "recommend", "quote": "If you need speech2text try this,", "excerpt": "If you need speech2text try this, https://ccoreilly.github.io/vosk-browser/", "context": "", "use_case": "speech-to-text in browser", "switched_from": "", "story": "Whistle: Speech to Text in 16.9 MB"}, {"id": 752887456, "item_id": 47055466, "url": "https://news.ycombinator.com/item?id=47055466", "by": "bruce343434", "date": "2026-02-17", "version": null, "stance": "recommend", "quote": "We also provide a websocket server and grpc server which can be used in telephony and other applications.", "excerpt": "https://alphacephei.com/vosk/install > We also provide a websocket server and grpc server which can be used in telephony and other applications. With bigger models adapted for 8khz audio it provides more accuracy.", "context": "", "use_case": "local speech recognition", "switched_from": "", "story": "Ask HN: What's the best realtime, local, TTS solution? Live call interpretation"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["speech recognition for input", "speech-to-text in browser", "wake word detection", "local speech recognition", "speech-to-text", "speech transcription"], "compared": [{"slug": "whisper", "name": "Whisper", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 801450784, "item_id": 50090674, "url": "https://news.ycombinator.com/item?id=50090674", "by": "mrkn1", "date": "2026-10-14", "version": null, "stance": "neutral", "quote": "", "excerpt": "this is such a poor model, I've tried it before. Try yapsnap it has better word error rate and runs super fast on CPU. https://github.com/kouhxp/yapsnap/", "context": "", "use_case": "speech recognition", "switched_from": "", "story": "Show HN: How random are you?"}], "threads": [{"url": "https://news.ycombinator.com/item?id=50074909", "title": "Show HN: How random are you?", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50054379", "title": "Show HN: GeoRadios \u2013 Spin a globe, hear what's on the radio there", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50008427", "title": "Whistle: Speech to Text in 16.9 MB", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49373051", "title": "Agent Voice, communicate with your coding agent all from Voice, on the fly", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47025861", "title": "Ask HN: What's the best realtime, local, TTS solution? Live call interpretation", "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": {"compare": 1}, "2025-12": {}, "2026-01": {"neutral": 1, "compare": 1}, "2026-02": {"recommend": 1}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {"neutral": 1}, "2026-09": {}, "2026-10": {"recommend": 2}}, "versions": [], "version_unnamed": 0, "quotes": [{"id": 801316032, "item_id": 50082252, "url": "https://news.ycombinator.com/item?id=50082252", "by": "vunderba", "date": "2026-10-14", "version": null, "stance": "recommend", "quote": "I went with Vosk because it's pretty trivial to lock input down to a set vocabulary", "excerpt": "OP here - I went with Vosk because it's pretty trivial to lock input down to a set vocabulary (in this case numbers) and from my testing works relatively well on most browsers. (webkit, firefox, etc) https://github.com/alphacep/vosk-api", "context": "", "use_case": "Speech recognition for input", "switched_from": "", "story": "Show HN: How random are you?"}, {"id": 800877696, "item_id": 50054856, "url": "https://news.ycombinator.com/item?id=50054856", "by": "sfpk", "date": "2026-10-12", "version": null, "stance": "neutral", "quote": "hooked it up to vosk", "excerpt": "I once had the idea to try to use talk-radio for language learning -- i did something like this and hooked it up to vosk, https://ccoreilly.github.io/vosk-browser/ . Since you've already categorized the talk-radio stations -- you could add this functionality -- I don't really think my idea was strong enough for a full SaaS business -- but it could complement your site.", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: GeoRadios \u2013 Spin a globe, hear what's on the radio there"}, {"id": 800168000, "item_id": 50010500, "url": "https://news.ycombinator.com/item?id=50010500", "by": "sfpk", "date": "2026-10-08", "version": null, "stance": "recommend", "quote": "If you need speech2text try this,", "excerpt": "If you need speech2text try this, https://ccoreilly.github.io/vosk-browser/", "context": "", "use_case": "speech-to-text in browser", "switched_from": "", "story": "Whistle: Speech to Text in 16.9 MB"}, {"id": 789968835, "item_id": 49373052, "url": "https://news.ycombinator.com/item?id=49373052", "by": "rat_rad", "date": "2026-08-20", "version": null, "stance": "neutral", "quote": "it uses a browser loaded, very lightweight vosk model", "excerpt": "AgentVoice is a bridge from your voice portal to your desired coding agent (claude code, cursor, codex) via an custom, global mcp server and more granular cli commands specific to the provider, such as new agent. For wake word detection, it uses a browser loaded, very lightweight vosk model, or a VAD model (silero VAD) instead of outsourcing the entire stream to speech to text provider. It does not actually use speec", "context": "", "use_case": "wake word detection", "switched_from": "", "story": "Agent Voice, communicate with your coding agent all from Voice, on the fly"}, {"id": 752887456, "item_id": 47055466, "url": "https://news.ycombinator.com/item?id=47055466", "by": "bruce343434", "date": "2026-02-17", "version": null, "stance": "recommend", "quote": "We also provide a websocket server and grpc server which can be used in telephony and other applications.", "excerpt": "https://alphacephei.com/vosk/install > We also provide a websocket server and grpc server which can be used in telephony and other applications. With bigger models adapted for 8khz audio it provides more accuracy.", "context": "", "use_case": "local speech recognition", "switched_from": "", "story": "Ask HN: What's the best realtime, local, TTS solution? Live call interpretation"}, {"id": 747832994, "item_id": 46739562, "url": "https://news.ycombinator.com/item?id=46739562", "by": "BiraIgnacio", "date": "2026-01-23", "version": null, "stance": "compare", "quote": "I've been looking into whisper and vosk in the last few days.", "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": "speech-to-text", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 743726785, "item_id": 46482924, "url": "https://news.ycombinator.com/item?id=46482924", "by": "EdNutting", "date": "2026-01-03", "version": null, "stance": "neutral", "quote": "transcription using Vosk", "excerpt": "A prototype of an auto-following autocue/teleprompter. Uses local-AI-only. It\u2019s a web app but not using in-browser transcribe. Ive found it to be way better for recording YouTube videos direct to-camera than the existing free apps which just scroll at a fixed speed. Open source at: https://github.com/ednutting/autocue Python server does the recording, transcription using Vosk (or choice of other models), and an algor", "context": "", "use_case": "speech transcription", "switched_from": "", "story": "Ask HN: What are you working on? (Jan 2026)"}, {"id": 734845265, "item_id": 45927829, "url": "https://news.ycombinator.com/item?id=45927829", "by": "sjsdaiuasgdia", "date": "2025-11-14", "version": null, "stance": "compare", "quote": "Whisper does much better than stuff I've tried in the past like Vosk.", "excerpt": "I use Whisper running locally for automated transcription of many hours of audio on a daily basis. For the most part, Whisper does much better than stuff I've tried in the past like Vosk. That said, it makes a somewhat annoying error that I never really experienced with others. When the audio is low quality for a moment, it might misinterpret a word. That's fine, any speech recognition system will do that. The proble", "context": "", "use_case": "", "switched_from": "", "story": "I think nobody wants AI in Firefox, Mozilla"}]}