Post

hear me out: speech-to-text that emits emojis

via sentiment analysis or? because a sentiment analysis on both the audio + text is something I've been cooking on.

I'm cooking up a middleware that is essentially a multi-step, emission per-step, voice digestion pipeline. There's a lot more around it, and it slots into my larger project. Think, mqtt topics that can be subbed to, some of which are sentiment outputs.