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.
Transcribing locally could be slow if the users GPU does not support CUDA. In that case it might be preferable to use the API instead. https://platform.openai.com/docs/guides/speech-to-text