This means it will sound like I am talking to someone in the podcast, when it's actually a clone of my voice and another AI voice talking to each other based on a script.

If so, could you provide a demo or visual guide on how it can be done?

Is there a limit on the duration of the audio recording?

Finally, how do you compare your system with the one from ElevenLab in terms of quality of the AI voices? Can you provide a side-by-side comparison table as of today July 2025?

Thank you.