Something like: enter your apikey to openai or elevenlabs, click book, click generate, audio is being produced and will show up

It doesn't have to be perfect but at least those basic steps without doing a bunch of manual hacking yourself.

• Update 2025-06-30 (PST) (AI summary of creator comment): The creator is looking for an integration that allows a user to easily flip back and forth between reading the text and listening to the generated audio.

• Update 2025-07-13 (PST) (AI summary of creator comment): The creator has specified that for a YES resolution, the integration should ideally treat the generated audio as another 'version' or format of the book (like epub, mobi, etc.).

An implementation that requires going through the 'edit book' UI to manage the audio is considered a point against a 'YES' resolution.

• Update 2025-07-13 (PST) (AI summary of creator comment): In response to a user, the creator has clarified their original intent for a YES resolution:

  • The integration must produce a portable and sharable audio file (e.g., an MP3).

  • The desired outcome is a tangible audio file that can be kept and listened to on other devices, not just a real-time "read aloud" feature within the Calibre application.