Hi!
I’m trying to use HyperTTS to create audio for my vocabulary.
On this deck, I have multiple words/sentences on every card. So basically, I would like to have a separate audio for every line on the back side of the card. These should be playable individually. So at the end of every line there should be a ‘play’ button.
Seems to me like this is currently not possible unless you do it manually using text selection. Anyone know some trick?
It sounds like you have all those words/sentences stacked up in a single field? This is a good example of why it’s generally better to keep things in separate fields.
You’ve already discovered the method of manually selecting the text you want to generate specific audio for. Beyond that, you might be able to do something more automated with Regext/Text Processing, but I’m not certain it would be scalable either. It’s pretty advanced, but you can explore that on your own, starting on the tutorial site – HyperTTS: Collection Audio .
On this deck the cards contain small pieces of dialog, that I want to learn together, like 3-4 sentences, which makes perfect sense to me.
For now, I will just forgo the audio, seems to be to much manual work. Text replacement with regular expressions cannot help me here, I think.
What could help is writing a script that works over the deck automatically, but I think HyperTTS has no api or anything …
Thanks anyway!