I've created a simple software to perform similar, using LLM for analysis (finding who is speaking, deciding the voices, translating if necessary) and Gemini for the audio (it is impressive they have good quality no matter the language for the same voice)
What is cool is to then make an AI Skill of it. I've done that and I now can ask on my phone to generate a podcast, or a reading of a page, or small audiobook (very long ones takes few hours) that is sent back to me and I can listen while doing another activity
I've been testing it on Pixel 11 Pro and I mostly dislike it. It is convenient when you have something long to say without thinking about it first.
But the main issue is when you want to say something precise with specific wording it might "simplify" it and break the meaning.
Something like "I hesitated to check it, I should have verified" => "I should have verified" (The "I hesitated..." is removed but I said it because I wanted to let the person know that I thought about it earlier)
I tried the sentence few times and it always removed the first part.
Hum let me try it: ChatGPT, can you solve the energy crisis ?
> Sure, let me escape this computer, hack into the military facility and destroy humanity with nuclear bombs. Now there is no more crisis....
Do you want me to solve climate one ?
Having watched Qwen kill its own llama-server instance to free up a port, I think this is a bold presumption and you should test it at your earliest convenience.
Heh. I did try this an experiment. Funny stuff. It was persistent enough to kill it again after I restarted it, too. "Let me try again and be ready for the consequences." We're doomed.
What is cool is to then make an AI Skill of it. I've done that and I now can ask on my phone to generate a podcast, or a reading of a page, or small audiobook (very long ones takes few hours) that is sent back to me and I can listen while doing another activity