Long shot, but wanted to see if any of the brains here on ES could help.
I’ve recently gotten into scripting AI gen videos - trouble is that they often will lack sound. I was thinking of going down the rabbit hole of adding dialog and effects to some of the videos I script, but have no idea where to start. Definitely don’t want to go down the road of paying a voice actor - they’re absolutely talented, but this use case isn’t worth it.
Wondering if there was an AI model that could convert text into “sensual/sexy” dialog that was somewhat easy to use.
I second ElevenLabs. There are tons of voices to choose from you will find some sexy seductive ones out there. I used these as well in my latest self-made video as well. You get 10k credits per month for free (one letter = one credit). Upgrading to paid tier starts at 5/month, where you get 20k credits. It’s actually pretty cheap and the quality of the voices are really good.
Give the free tier a try first, play a bit with it and see if you find a good and fitting voice. Create some lines and see if they fit the video. If you need more credits, you can upgrade later.
A new open source model series from Qwen just dropped: Qwen3-TTS. Seems a good option to do local TTS with a fair amount of control over the voice design.