looks like an analogue to stable diffusion for voice is whisperspeech which functions ok<div><a href="https://colab.research.google.com/drive/1xxGlTbwBmaY6GKA24strRixTXGBOlyiw">https://colab.research.google.com/drive/1xxGlTbwBmaY6GKA24strRixTXGBOlyiw</a></div><div dir="auto"><br></div><div dir="auto">“quick! to the batporter! the ginseng hives are modulating!” low quality, baseline voice</div><div dir="auto"><br></div><div dir="auto"><br></div>