Add a transcription to the live conversation. Fetch the text from the STT and TTS in the backend, and display it in the frontend. No need for much styling.
Frontend:
Backend:
These files have been added/changed to allow the user to receive live translation into english by talking:
- record themselves talking
- send that audio blob to the backend
- process it in a STT -> LLM (translation into English) -> TTS pipeline in the backend
- send translated audio blob back to frontend
- plays audio blob to user
At Bottom of page:

Add a transcription to the live conversation. Fetch the text from the STT and TTS in the backend, and display it in the frontend. No need for much styling.
Frontend:
Backend:
These files have been added/changed to allow the user to receive live translation into english by talking:
At Bottom of page:
