My organization puts together KubeCon + CloudNativeCon, the largest open-source developer conferences. We want to offer real-time transcription (also known as open captioning) for the hearing impaired and those who speak English as a second language. And, we'd also like to offer real-time, on screen translation for the events we'll be holding in Seoul, Shanghai, São Paolo, and elsewhere.

Can anyone offer suggestions for the state-of-the-art around transcription and translation? There seem to be a number of small vendors with questionable back-ends and then Amazon, Google, and Microsoft with powerful APIs but no front-end integration to capture onsite audio and send back the transcription and translation feeds.

Has anyone seen a vendor that has good onsite integration and lets you tap into the most capable APIs?