Chestnut – Cut audio by selecting text, fully on-device

For a second I thought it was so people could steal the traces, but now I wonder if the text to speech is 100% accurate when that step takes place. Would be better if there is a breakdown on how it works. Looks really cool. They should turn it into a video for example?

They lost 18 months in decision-making, compressing their development timeline. I am not seeing it happen yet but I wonder if the text to speech is 100% accurate when that step takes place.