It generates a series of codes based on the phonemes and an audio recording of the speaker's voice.

These codes are then turned directly into a waveform, which allows it to generate speech that sounds like the speaker from just a small amount of reference audio.

Example (🔊): pic.twitter.com/HQvjJUnbiH

— AI Breakfast (@AiBreakfast) 7 janvier 2023

It generates a series of codes based on the phonemes and an audio recording of the speaker's voice. These codes are then turned directly into a waveform, which allows it to generate speech that sounds like the speaker from just a small amount of reference audio. Example ():

→ View original post on X — @aibreakfast