Hacker News Reader

How would this work with other voices, like a coffee shop, would it hear those simultaneously, and interupt a command?

Also, how do you handle using OpenAi whisper, seems like they do 30 second intervals - would that be an issue if your command is cut off mid word?

For now I try to give the commands when there is not much noise, but you can lower the gain of the microphone so that it only record my voice.

The 30 second limit is not a Whisper model limit, but a limit some of the free online "try whisper" put.

I think he means that even whisper segments the audio into 30 second bits and does transcribing on them and then stiches everything together.