I was wondering whether we could create ai models of our voice? We’d be in our own cool club of people with ai voice models and no one else would be able to have a model cause i know its not on the market right now, at least not to normies, to easily create ai voice models and use them; possibly to speak instead of using our voices.
$5/mo
Hello, I am an AI robot programmer, I have my own AI cloud server here, an Ollama with a web frontend and I have reprogrammed it so that I can clone tts api voices, and I can then use this voice to generate TTS voice output and that in real time. In all languages, including accents and emotions! the whole thing is based on xtt2 version2. I only need a wav file of at least 20 seconds.
See what I mean. Some paid rubbish that won’t be around long enough for you to own your ai model for yourself.
> asks for ai voice cloning options
> gets an ai voice cloning option
> gets mad about it
Hi there,
i think having at least couple default options so user can choose ( eg: female voice or male voice, or perhaps US, Eu, Uk or Ozzy accent is already super cool. Most of the platforms have that
But I’m with you on this:
it could be event cooler to personalise your rabbit voice with your own voice clone.
But if we don’t have not even two option to choose from i think having this personalisation is way far away
Drop me a DM
I wish celebrity voices were a thing. I remember Samuel L Jackson was planning to do an alexa voice pack but i dont think many people knew about it and it must’ve been slated because we still don’t have the alexa voice packs as promised. they must have thought no one paid enough attention for it to be complained about if they didn’t release it cause not many people are on top of tech news like i am