[Neolio]

Since it's on macos, I use optimized both whisper and parakeet, based on if you need accuracy. Parakeet is almost real-time.

[Leftium]

Sure,there are models that are 30X realtime, but not streaming: the transcription doesn't start until after the utterance is complete.

So realtime streaming seems even faster. If the transcription started out bad, you can cancel and restart within a few words, before the utterance is over.