search

yacineMTB / talk

Let's make sand talk
587 stars 43 forks source link

Speaker use: Differentiate between AI and user voices #37

Open choombaa opened 1 year ago

choombaa commented 1 year ago

Since the microphone is always listening, the AI will create a feedback loop with its own outputs if headphones aren't used. We could potentially differentiate between voices.

KixxA1 commented 1 year ago

Hi

jmanhype commented 1 year ago

Hi

yacineMTB commented 1 year ago

I noticed this too can you filter voices out? I guess zoom & macos do this

yacineMTB commented 1 year ago

Maybe we should consider whisperX (and also abstract whisper over an HTTP interface)

yacineMTB commented 1 year ago

oh fuck yeah, check it out https://github.com/ggerganov/whisper.cpp/pull/1058

image

choombaa commented 1 year ago

Very cool, putting this on my todo list