The initial rationale for speech-to-speech systems was that speech-to-text conversion loses emotional information, while speech-to-speech systems can respond in a manner matching the speaker’s emotion.

“Like let's talk about like why did people start thinking about speech to speech. And so the initial idea was simple that hey if you convert speech to text it's going to lose the emotional information,”

“So if you say hey you might be saying it in a sad way or an excited way,”

“the bot is going to answer in the same manner,”

“right? So that was the obvious reason people started.”