{"slug": "faster-whisper", "name": "faster-whisper", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 4, "commenters": 6, "warners": 0, "score": 4.155, "rising": 0.02, "first": "2026-01-09", "latest": "2026-10-07", "why": "Thanks to faster-whisper and local models using quantization, I use it in all places", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 2, "compare": 0, "warn": 0}, "spark": [0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1], "listed": true, "loved": [], "caveat": "", "short_quote": "Thanks to faster-whisper and local models using quantization, I use it in all places", "icon": true, "domain": null, "github_repo": "github.com/systran/faster-whisper", "official_url": "https://github.com/SYSTRAN/faster-whisper", "pricing": "", "aliases": ["faster-whisper"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 799829984, "item_id": 49989374, "url": "https://news.ycombinator.com/item?id=49989374", "by": "amne", "date": "2026-10-07", "stance": "recommend", "quote": "faster-whisper produces the text then onnx scores all my HA entities", "excerpt": "I switched to a decision model for my local \"AI\" voice control thingy. faster-whisper produces the text then onnx scores all my HA entities to determine which one I'm talking about .. then it lists all its actions and a second scoring round to determine what action I want. some regex to extract numbers if I'm saying things like \"water the lawn for 10 minutes\". It's pretty dumb when compared to what an LLM can do but ", "context": "", "use_case": "local voice control speech-to-text", "switched_from": "", "story": "Jev-Driven SRE Diagnosis: What Worked and What Failed"}, {"id": 783434912, "item_id": 48964682, "url": "https://news.ycombinator.com/item?id=48964682", "by": "wolvoleo", "date": "2026-07-18", "stance": "recommend", "quote": "I'm really happy with faster-whisper on a GPU.", "excerpt": "Looks interesting, I'll give it a try. Though I'm really happy with faster-whisper on a GPU.", "context": "", "use_case": "speech transcription on GPU", "switched_from": "", "story": "Transcribe.cpp"}, {"id": 752683809, "item_id": 47042738, "url": "https://news.ycombinator.com/item?id=47042738", "by": "sathish316", "date": "2026-02-16", "stance": "recommend", "quote": "Thanks to faster-whisper and local models using quantization, I use it in all places", "excerpt": "To build your own STT (speech-to-text) with a local model and and modify it, just ask Claude code to build it for you with this workflow. F12 -> sox for recording -> temp.wav -> faster-whisper -> pbcopy -> notify-send to know what\u2019s happening https://github.com/sathish316/soupawhisper I found a Linux version with a similar workflow and forked it to build the Mac version. It look less than 15 mins to ask Claude to mod", "context": "", "use_case": "local transcription", "switched_from": "", "story": "Show HN: Free Alternative to Wispr Flow, Superwhisper, and Monologue"}, {"id": 744940849, "item_id": 46558803, "url": "https://news.ycombinator.com/item?id=46558803", "by": "satvikpendem", "date": "2026-01-09", "stance": "recommend", "quote": "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"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["local voice control speech-to-text", "speech transcription on gpu", "real-time mandarin subtitling", "speech-to-text", "local transcription", "speech transcription"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49986765", "title": "Jev-Driven SRE Diagnosis: What Worked and What Failed", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48963879", "title": "Transcribe.cpp", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48894752", "title": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48555835", "title": "I Fired Google", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47040375", "title": "Show HN: Free Alternative to Wispr Flow, Superwhisper, and Monologue", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46527706", "title": "Dell's CES 2026 chat was the most pleasingly un-AI briefing I've had in 5 years", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"recommend": 1}, "2026-02": {"recommend": 1}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {"neutral": 1}, "2026-07": {"neutral": 1, "recommend": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {"recommend": 1}}, "quotes": [{"id": 799829984, "item_id": 49989374, "url": "https://news.ycombinator.com/item?id=49989374", "by": "amne", "date": "2026-10-07", "stance": "recommend", "quote": "faster-whisper produces the text then onnx scores all my HA entities", "excerpt": "I switched to a decision model for my local \"AI\" voice control thingy. faster-whisper produces the text then onnx scores all my HA entities to determine which one I'm talking about .. then it lists all its actions and a second scoring round to determine what action I want. some regex to extract numbers if I'm saying things like \"water the lawn for 10 minutes\". It's pretty dumb when compared to what an LLM can do but ", "context": "", "use_case": "local voice control speech-to-text", "switched_from": "", "story": "Jev-Driven SRE Diagnosis: What Worked and What Failed"}, {"id": 783434912, "item_id": 48964682, "url": "https://news.ycombinator.com/item?id=48964682", "by": "wolvoleo", "date": "2026-07-18", "stance": "recommend", "quote": "I'm really happy with faster-whisper on a GPU.", "excerpt": "Looks interesting, I'll give it a try. Though I'm really happy with faster-whisper on a GPU.", "context": "", "use_case": "speech transcription on GPU", "switched_from": "", "story": "Transcribe.cpp"}, {"id": 782398832, "item_id": 48899927, "url": "https://news.ycombinator.com/item?id=48899927", "by": "tapland", "date": "2026-07-13", "stance": "neutral", "quote": "I use Systran/faster-whisper-medium for real-time subtitling", "excerpt": "I use Systran/faster-whisper-medium for real-time subtitling, but you need to get used to the context it's used it and the weirdness it translates into. Parakeet has great mandarin>CN text, but running that + a translation model has been tricky and I never got it fast.", "context": "", "use_case": "real-time Mandarin subtitling", "switched_from": "", "story": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor"}, {"id": 776902612, "item_id": 48556413, "url": "https://news.ycombinator.com/item?id=48556413", "by": "pwython", "date": "2026-06-16", "stance": "neutral", "quote": "Voice input is openWakeWord for the wake word plus faster-whisper for speech-to-text, all on-device.", "excerpt": "I had Claude whip up a local solution for me using Gemma 4 26b-a4b on my Mac and a Raspberry Pi Zero 2 W. It can do web search (valyu), file reading -- I have business & personal context stored in many markdown files -- weather, Apple reminders, and has cross-session memory. Streamline but capable agent that has been pieced together over a few weeks after using Karpathy's LLM wiki pattern, with bits of Hermes logic. ", "context": "", "use_case": "speech-to-text", "switched_from": "", "story": "I Fired Google"}, {"id": 752683809, "item_id": 47042738, "url": "https://news.ycombinator.com/item?id=47042738", "by": "sathish316", "date": "2026-02-16", "stance": "recommend", "quote": "Thanks to faster-whisper and local models using quantization, I use it in all places", "excerpt": "To build your own STT (speech-to-text) with a local model and and modify it, just ask Claude code to build it for you with this workflow. F12 -> sox for recording -> temp.wav -> faster-whisper -> pbcopy -> notify-send to know what\u2019s happening https://github.com/sathish316/soupawhisper I found a Linux version with a similar workflow and forked it to build the Mac version. It look less than 15 mins to ask Claude to mod", "context": "", "use_case": "local transcription", "switched_from": "", "story": "Show HN: Free Alternative to Wispr Flow, Superwhisper, and Monologue"}, {"id": 744940849, "item_id": 46558803, "url": "https://news.ycombinator.com/item?id=46558803", "by": "satvikpendem", "date": "2026-01-09", "stance": "recommend", "quote": "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"}]}