I'm looking for a tool that has the ability to upload samples of someone's audio content, cloning their voice but also creates output based on their style.
I know ElevenLabs would be great for voice cloning. But I'm stuck at the part where the voice would need to output something unique based on what they were saying in the samples. Sort-of like building a persona on that person and doing unique speech in their cloned voice.
Does anyone know what tool(s) would be best to do this?
[link] [comments]