If you're willing to forgo the interactive LLM bit, kokoro-tts (just a script using Kokoro-ONNX) takes epubs and outputs a series of wavs or mp3s that need to be stitched together into chapters or audiobook m4a with some ffmpeg fu. I've listened to several generated audiobooks, and found them pretty good. Some nice generic narration-like prosody. It uses espeak-ng to generate phonemes and passes those to the model to render voice, so it generally pronounces things quite well. It comes with a handful of nice voices and several can be blended, but no easy voice cloning, like chatterbox, that I'm aware of.

https://github.com/nazdridoy/kokoro-tts/blob/main/kokoro-tts