Could we geocode the lecture-snippets, so the statements persist at location? That way, one could advance at ones own pace. Or map it to a route of ones own design, while keeping the pace..

I recall projects that did something like this. Besides museums and historic neighborhoods, one memorable application was at a graveyard. Reenactors read letters and diary entries written by the deceased. The closer you were to the writer's tombstone, the louder their audio. From far away all you heard was a combination of barely audible voices. I believe the relevant terms are "audio walks" or "phonoscapes".

I have created something similar for a museum. I placed bluetooth beacons behind the exhibits, and when visitors approached them the app automatically switched to the "page" for this exhibit. The app was able to display texts, videos, images and audio files.

Bloomberg Connects[1] is an attempt to do something like this. An institution connects their CMS and then visitors can access additional text, audio, video, images using triggers in the museum space.

However, to my knowledge it does not support live synchronous audio.

[1] https://play.google.com/store/apps/details?id=org.bloomberg....

Alcatraz almost has this!

Due to the pandemic they made an app where you can follow along and listen to different parts of the tour

It’s not very “smart” I.e. not location aware to start the next prompt but honestly much better than those clunky audio tour boxes

The museum would lose revenue because you wouldn’t have to pay to rent their audio devices.

I am a software dev for a company that builds museum exhibits. Many museums these days have bespoke web or downloadable apps that serve audio tours, sometimes activated based on location through QR codes, computer vision, beacons (iBeacons, Eddystone beacons), or RFID scannable bracelets given to every visitor.

Could you please pitch this app as a more scalably-profitable revenue stream for your employer?

It's not really "an app". Every museum wants a different MVP, and I just listed some of the common tech involved in most of them. We don't have a turnkey product for this, we build out a custom thing every time, because clients come to us specifically for one-of-a-kind technical implementations.

Aruba Networks does this with their Meridian division.

You could pay for access to the audio stream just as well.

A lot of tour buses catering to speakers of foreign languages do exactly this.