What MemoFlow does with this language
| Live captions while recording | Yes, when connected. Meeting minutes bill at 1 Credit / minute on Basic and Plus; Pro includes a monthly allowance. |
|---|---|
| Transcript after recording | Plus and Pro. The whole session is recognised again automatically when it ends; if that cannot finish safely, the live transcript is kept. |
| Speaker labels | Plus and Pro. Numbered speakers where attribution is confident; you can rename them. |
| Live Interpretation from Korean | Yes — into any of the 33 target languages except Korean itself. |
| Live Interpretation into Korean | Yes — from any of the other 29 transcription languages. |
| Meeting summary | Plus and Pro. Drafted from a saved note as a separate result; the transcript is not overwritten. |
| Search | Save the transcript as a note and its words appear in note search. |
| Platforms | iPhone (iOS 16.0+) and Android (8.0 (API 26)). No desktop or web app. |
Before you record
Set the Speech Recognition Language to 한국어. The session listens for Korean only, which matters in business meetings where English acronyms and product names are said inside Korean sentences: expect to check how those were written.
Names are the other thing to read against the audio. Speaker labels arrive as numbers after refinement; rename them once and the names carry through the transcript.
Spacing is part of the result
Korean separates word units with spaces (띄어쓰기), and a recogniser can place them differently from how you would write them. Note search matches whole words and the beginnings of words, so if a phrase you expect does not turn up in a saved transcript, search for the start of its first word instead.
Spacing is also why MemoFlow's ASR benchmark method reports Korean character error rate alongside word error rate: a result can look worse by words while the characters are right. No Korean result has been published yet.
Korean with Japanese, Chinese or English speakers
Korean is a source and a target in Live Interpretation, so a session can follow a Korean speaker in Japanese, Chinese or English, or the reverse. Each session runs one direction, and the original stays next to the machine translation for checking.
Limits to know
- The language is chosen before recording; there is no automatic language detection.
- Live captions need a connection. Offline recording continues without them.
- No accuracy figure is published for any language.
- Machine translation, not a human interpreter.
- Honorific levels and dialects have not been evaluated separately.