A tiny Rust menu bar app for macOS. Hold Fn to activate the mic, speak, release to paste. Audio streams to Deepgram Nova-3 in real time — no batch delay. Falls back to Groq Whisper. Open source, free.
Hey! I built FnKey because I wanted macOS dictation that actually feels instant. Most voice typing tools use Whisper in batch mode — you record, wait, then get text. FnKey streams audio to Deepgram Nova-3 over WebSocket while you speak, so transcription is ready the moment you release the Fn key. The mic is only active while you hold the key — privacy by design. Open source, Rust, GPL-3.0. Would love your feedback!
Looks cool! Does it handle technical jargon well out of the box — model names, CLI flags, that kind of thing? That's usually where dictation tools fall apart i felt
This sound like a very useful app, Do you guys plan to support importing voice from audio stream, like from Teams or Slack?
Because let's say my team speaks French or Portuguese, I just click the button and it would start streaming my team audio to the transcription service And it would translate almost instantly
I know that teams supports something similar, but it is not flexible in terms of models, And if you guys stream it directly from the computer audio source, it might be better
Built in Rust, streaming to Deepgram over WebSocket, and open source. That's a solid stack. How accurate is the transcription for technical jargon or code related terms like function names and variable names? Would love to use this for dictating code comments. Nice work on shipping this!
Interesting take on trying to optimize on latency. I would be more interested in how dictation tools handle punctuation, formatting text, removing filler words, etc. Congrats on launch!
Been using Deepgram's streaming API for call-center transcriptions - the latency is wild. Curious how FnKey handles overlapping speech when you're dictating code while thinking aloud? My current workaround is pausing like a Victorian telegram, which defeats the purpose of stream processing.
Eugene