SevaSk / ecoute

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.

https://github.com/SevaSk/ecoute

Only record microphone/speaker input on keypress

Kindred0102 opened this issue 3 months ago · comments

Kindred0102 commented 3 months ago

How and where would I make it so it only records audio when I'm holding a key like "TAB", so I can mitigate the amount of tokens used?
Would it be in main.py or audiorecorder.py?