Diagram

Background: How do we Create Text to Speech?

Why?

Overview of how it works

Creating an audio clip — Demo / Eleven Labs Overview

• demos/tts_openai.py
• demos/tts_elevenlabs.py
• The main difference is the ElevenLabs one has a lot more voices!

Passing the audio to S3 bucket

text_to_audio

Creating an S3 Bucket

• ON THE FLY
• Getting the name
• Getting the region

Get the playable URL and pass it to the S3

Pass everything to the frontend.

Go through the user workflow again