# whisper.cpp

33 Hacker News commenters recommended whisper.cpp and 1 criticized it, November 2025 to November 2026. It was recommended in 11 of 13 months; owners who said how long report a median of 2 years (4 owners). It meets the Hacker Approved badge rule.

**Verdict:** Fast, free, fully local speech-to-text that people run for dictation, subtitles and meetings. Critics say speed depends heavily on hardware, especially without a high-end GPU.

## Why people recommend it

- Runs locally across platforms (5 comments): "The moat here is local inference. Whisper.cpp + Metal gives you <500ms latency on M1 with the small model." ([source](https://news.ycombinator.com/item?id=47047049)) "A local-only voice to text whisper.cpp transcriber I can globally use while holding ctrl-semicolon." ([source](https://news.ycombinator.com/item?id=47248368)) "tend to just work perfectly, across a whole bunch of different platforms and hardware backends" ([source](https://news.ycombinator.com/item?id=48142110))
- Fast transcription, even on CPU (5 comments): "works at 6x realtime transcription speed on my four-core ~2.4GHz laptop, and doesn't really stress CPU or memory" ([source](https://news.ycombinator.com/item?id=47052351)) "The performance of whisper.cpp allows me to transcribe 1h of meeting in just 20-30s" ([source](https://news.ycombinator.com/item?id=47014040)) "Whisper.cpp/Faster-whisper are a good bit faster than OpenAI's implementation" ([source](https://news.ycombinator.com/item?id=45843564))
- Good output quality (4 comments): "technical terms are going to be just fine with Whisper" ([source](https://news.ycombinator.com/item?id=45932638)) "it detects very well my very-local spanish modisms" ([source](https://news.ycombinator.com/item?id=49483685)) "leaps and bounds better in terms of output quality" ([source](https://news.ycombinator.com/item?id=49935825))
- Reliable day to day (3 comments): "tend to just work perfectly, across a whole bunch of different platforms and hardware backends" ([source](https://news.ycombinator.com/item?id=48142110)) "it just keeps on working without any issues" ([source](https://news.ycombinator.com/item?id=48966757)) "has been pretty solid for me" ([source](https://news.ycombinator.com/item?id=48275469))

## What people warn about

- Slow on some hardware or workloads (4 comments): "Whisper gives decent performance as far as speed goes only on a pretty top-end GPU" ([source](https://news.ycombinator.com/item?id=48971073)) "whisper.cpp is awesome but even it just can't process a three-hour vid in seconds" ([source](https://news.ycombinator.com/item?id=49636858)) "yet it completes in a fraction of the time using batching" ([source](https://news.ycombinator.com/item?id=46558803))

## Alternatives hackers recommend

- [OpenAI Whisper](https://hackerapproved.com/p/whisper.md): 164 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
- [Transcribe.cpp](https://hackerapproved.com/p/transcribe-cpp.md): 21 recommend

## Cite as

Hacker Approved, "whisper.cpp", https://hackerapproved.com/p/whisper-cpp/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).