If you want to test it with multiple languages, perhaps try all the parliaments of the world? They tend to have public recordings.
Right now, speaker identification (and thus everything downstream that depends on that) works better for meetings where Circleback joins the call (compared to those imported) but I wanted to share this anyway.
I think the thing I'd like most is if the AI could "cite" its source (i.e. provide a timestamp of when exactly the statement was made that it's summarizing) directly inline in the summary (vs. only in the transcript).
Similarly to how they're used in AI-powered search (e.g. Perplexity), inline citations would help me easily cross-reference statements and gain confidence that the summary is accurate and the information can be relied on.