SuperwhisperSSuperwhisper

Speaker identification for "Transcribe File" (who said what)

Meetings already separate and label speakers on my Mac, but "Transcribe File" returns a plain transcript, with no option to turn speaker identification on. Many of my recordings come from elsewhere: interviews, calls recorded in other apps, voice memos with several people. They need the same "who said what" as Meetings. Requested: - A "Identify speakers" option when transcribing a file, plus a CLI flag (e.g. superwhisper transcribe --speakers) - An optional expected number of speakers, for better accuracy - Speaker labels I can rename, like in Meetings, and that are kept in copies and exports - Recognizing speakers I've already named, if possible
PendingPending

This would be valuable! A real killer-app feature. The WAVE AI note-taking and recording tool at wave.co has the edge in this kind of feature. One of the first affordable options I've found that remembers people's voices. I wouldn't even need a second meeting app anymore; just Superwhisper!!

If it's not much of an ask, I would like that. Is there any way we can export the SRTs subtitles as well? Because so far, Superwhisper has the best speech to text options available. Like it caters every language and it goes through another layer to fix all of the available mistakes. So I'm thinking if we can get subtitles as well, that will be a huge plus because that will help immensely when it comes to some sort of like video editing as well or creating shorts. In different languages with ease.

This really is a must-have