iamjackg
Joined 5 years ago
Joined 5 years ago
- the TTS voice sounds way too excited for something meant to be relaxing
- the sudden speaking after 10 seconds of silence is very jarring -- I wonder if something like a reverse-reverb effect would be enough to "warn" the brain that a new sentence is incoming. There's an example of how to do it in Ableton on YouTube[0] but the basic concept is: take a short slice of audio from the beginning of the sentence, reverse it, apply a long reverb, reverse it again, trim the end a little. You get a sort of ghostly aspirated sound that leads perfectly into the original sample.
That's a little uncharitable. I get where it's coming from, because I also still feel a tinge of (hypocritical) disappointment when I realize things are built with LLMs, but I truly think we need to start moving past this. It's not a giant corporation trying to scam you out of your hard earned money by passing slop off as a lovingly crafted product: it's somebody's pet project, somebody who clearly had a fun "what if" idea and was able to materialize it over time, with a TBD amount of care/iteration/refinement. I think it's something worth engaging with. Worst case scenario it sucks, like many cheapo projects do -- best case scenario it's awesome and/or it sparks a new interesting idea in somebody else.
0: https://en.wikipedia.org/wiki/Donald_in_Mathmagic_Land