NewsLab
Aug 28 13:40 UTC

Show HN: FnScribe – Open-source, offline dictation for macOS (github.com)

17 points|by modagent||9 comments|Read full story on github.com

Comments (9)

9 shown
  1. 1. modagent||context
    I built FnScribe because I'm pretty privacy concious and wanted a wispr flow-like app that kept everything local and on device. Currently works for Mac (sillicon and intel).

    It's dead simple. Hold the fn key, speak and release. I use a quantized Wisper small.en model for transcription. It inserts the text into the active application. There's also a hands-free model for longer dictation. Audio transcription is kept in memory. There's no account or transcription history. Clipboard contents are restored after it inserts it. GPLv3, Mac-only, English only..still in alpha. Hope you enjoy it! Would love some feedback.

  2. 2. e40||context
    Are you aware of Spokenly? It has a local mode that uses Apple’s built in services. I bind it to right command and use it frequently for hard to spell words.
  3. 3. DzHiBaS||context
    also handy.computer is awesome. local. choose your own model. multilingual. bind to any shortcut. works on arm silica
  4. 4. diwash007||context
    nice one.
  5. 5. itsdesmond||context
    I see that it changes the menu bar icon to indicate status. How is this communicated when windows are full screen and the menu bar isn’t visible?
  6. 6. djx22||context
    You may want to look into different models that are more accurate and maybe an AEC layer to remove background noise. Or at the very least a RNN de-noiser on the mic channel. Also, you may want to stream audio to the model instead of holding it all in memory and transcribe at the very end as that can potentially allow you to take the app much further than it is now.

    I see Claude implemented a very crude upsampling/downsampling algorithm, which is what LLMs usually do when prompted to handle such a problem. But I would suggest restraining the model from implementing DSP processing on their own and instead use battle tested libraries. You can use rubato's FFT Resampler.

    Audio processing is genuinely a hard engineering problem, LLMs usually don't get it right. If you decide to get deep into it, the knowledge you'll get is very rewarding.

  7. 7. zackify||context
    https://voxtype.io/

    https://tryvoiceink.com/

    There's so many of these, at this point I've seen 10 clones make the front page each time as if there never existed local only options before.

    Also whisper is pretty outdated vs parakeet

  8. 8. djx22||context
    It's because vibe coded apps have flooded the internet. This one is no exception. The feedback loop is now real: LLMs train from github on their own produced slop which they feed into the apps people build and publish on github to show off their "skills". In 2 years from now LLMs will become dumber and dumber as the rate of quality code vs. slop will be greatly imbalanced so, naturally, the more slop you have the more probable is that the LLM will use it for its answers. The death of software engineering is real.
  9. 9. ahaferburg||context
    Are you aware of https://handy.computer/?