Quentin Fuxa

Hey can you try with https://github.com/QuentinFuxa/WhisperLiveKit/releases/tag/0.1.7 ? VAC is functional in this released

On mac OS this can be done at system level using [BlackHole](https://github.com/ExistentialAudio/BlackHole). I will check on windows, if I don't find a similar loopback solution, I will add an option...

Yes. Haven't looked at it yet, but if that works, I'll try to do a release end of week

There is no other choice than launching a python script on the client side. It would means, on client side : - a little script with PyAudioWPatch + websocket (pip...

Hi, Regarding the first issue, if you don’t have a dedicated GPU, performance can suffer significantly. One potential workaround is to process the audio in smaller chunks, which seems to...

Hey, diarization lag has been drastically reduced in 0.1.9 release

For information I am working on implementing a more state of the art live diarization solution in whisperlivekit. Probably not in the next release however

Thank you for reporting this issue. It seems likely that the problem lies in the version of the OpenAI Python library you have installed. I tested a similar setup using...

Hi ! > What test audio do you use ? I use an AI audio generated using vidnoz with different speakers, and blackhole to redirect output to input audio from...

I will have a look at it. The difficulty here is to make it streaming