# OpenAI Whisper 164 Hacker News commenters recommended OpenAI Whisper and 53 criticized it, November 2025 to November 2026. It was recommended in 12 of 13 months. It meets the Hacker Approved badge rule. **Verdict:** A free, open speech-to-text model people run locally for accurate transcription and dictation across many languages, though it tends to invent text during silence and garble names. ## Why people recommend it - Highly accurate transcription (8 comments): "When OpenAI released Whisper, it was by far best-in-class, and they haven't released any major upgrades since then." ([source](https://news.ycombinator.com/item?id=47031609)) "this uses the Whisper Large model which is quite a bit better than the Youtube auto generated ones" ([source](https://news.ycombinator.com/item?id=49477218)) "the open whisper model which really is great especially if you use the larger parameter versions" ([source](https://news.ycombinator.com/item?id=48202672)) - Runs locally and privately (7 comments): "Combined with Whisper+ from F-Droid and you have a nice way to input voice as text from everywhere." ([source](https://news.ycombinator.com/item?id=48359024)) "free, OSS dictation tools that can run on-device, that are so much better than Apple's dictation" ([source](https://news.ycombinator.com/item?id=47006680)) "The best workaround is a third party app that lets you run Parakeet V3 or Whisper on your phone." ([source](https://news.ycombinator.com/item?id=49702453)) - Great for everyday dictation (5 comments): "I always get much better results in a lot faster time when i just turn on the mic and have whisper transcribe" ([source](https://news.ycombinator.com/item?id=46574660)) "Parakeet and Whisper are much smaller and perform great for quick dictation and transcription of longer files" ([source](https://news.ycombinator.com/item?id=47933890)) "polishing Whisper speech to text output, so I can dictate things to my computer and get coherent sentences" ([source](https://news.ycombinator.com/item?id=46363551)) - Pairs well with LLM pipelines (4 comments): "For this use case I think best bet is still a toolchain with a transcription model like whisper fed into an LLM to summarize" ([source](https://news.ycombinator.com/item?id=45971240)) "polishing Whisper speech to text output, so I can dictate things to my computer and get coherent sentences" ([source](https://news.ycombinator.com/item?id=46363551)) "I have built an ambient todo list / health data extractor using Gemma 4 2EB and Whisper" ([source](https://news.ycombinator.com/item?id=48087637)) ## What people warn about - Hallucinates text during silence (5 comments): "I read somewhere it comes from training on YouTube audio and happens when there is silence" ([source](https://news.ycombinator.com/item?id=47990553)) "It might make up a bunch of words, like "subtitles by soandso", when there's silence" ([source](https://news.ycombinator.com/item?id=45924201)) "tends to generate plausible-in-context content when there are long gaps or silence" ([source](https://news.ycombinator.com/item?id=49370627)) - Mangles names and technical jargon (3 comments): "Whisper often mistook actual words I say and hallucinate all the time when speaking technical jargon." ([source](https://news.ycombinator.com/item?id=47405202)) "generated subtitles with Whisper (with every single sentence having at least some mistake)" ([source](https://news.ycombinator.com/item?id=46105144)) "The issue with Whisper is that it messes up both names of both products and guests." ([source](https://news.ycombinator.com/item?id=46453505)) - Drops sentences or repeats with speakers (2 comments): "One thing all these models do (including whisper) is just omit full sentences, it's the worst thing a model can do." ([source](https://news.ycombinator.com/item?id=47594825)) "Whisper is really good for 1 person speaking. With more people you get repetitions." ([source](https://news.ycombinator.com/item?id=46742457)) - Setup and hardware compatibility hassles (3 comments): "current versions of Whisper GPU will not run on my not-quite-10-year old Pascal GPU anymore" ([source](https://news.ycombinator.com/item?id=46075228)) "Installing and running Whisper locally just to get notifications seems like more resource consumption than some of us are looking for." ([source](https://news.ycombinator.com/item?id=45929377)) "having real trouble to set up working environment for any Whisper derivatives after migrating to Fedora" ([source](https://news.ycombinator.com/item?id=46414686)) ## Alternatives hackers recommend - [NVIDIA Parakeet](https://hackerapproved.com/p/parakeet.md): 144 recommend - [Mistral Voxtral](https://hackerapproved.com/p/voxtral-transcribe-2.md): 69 recommend - [Moonshine open-weights STT models](https://hackerapproved.com/p/moonshine.md): 37 recommend - [whisper.cpp](https://hackerapproved.com/p/whisper-cpp.md): 33 recommend - [Transcribe.cpp](https://hackerapproved.com/p/transcribe-cpp.md): 21 recommend ## Cite as Hacker Approved, "OpenAI Whisper", https://hackerapproved.com/p/whisper/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).