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
MIT License
5.89k stars 827 forks source link

Use a different function for the response suggestions? #19

Closed MustaphaU closed 1 year ago

MustaphaU commented 1 year ago

Would it be possible to use a different API or function for the response suggestions? In my experience, I have not not been able to use that functionality due to always exceeding my quota. Are there any other free or opensource models that can be used in place of OpenAI gpt-3.5-turbo-0301 ?

image

SevaSk commented 1 year ago

While there may be other free or open-source models to choose from, this project utilizes the OpenAI GPT for its superior performance. If you're interested in modifying the code to employ other models, feel free to do so! I believe the only changes in the code would be in the generate_response_from_transcript method.

MustaphaU commented 1 year ago

I agree -- OpenAI's GPT is superior to most other similar models. Thanks for the tip, also for putting this together.