Hacker News

points by montenegrohugo 2 days ago | 0 comments

A key part of mine is using voice input to give max context quickly to my agents. I know some solutions exist, but on Linux they all frankly suck

So I made my own. Including patching onnx myself to run parakeet model (way better than whisper)

Fully FOSS: voiceio.dev

[–] pcthrowaway 2 days ago

Do you know if this could work on an Android phone eventually? Or do you have plans to make a hook for mobile apps that can stream the audio to a custom Linux server?