Use v2.16 for projects requiring fast, mostly-accurate captions (interviews, vlogs, documentaries). For technical content, heavy accents, or dense multi-speaker recordings, combine Speech to Text with a manual pass or glossary/custom vocabulary entries.

Earlier versions of Speech to Text required a cloud connection for transcription. v2.16 includes a (downloadable as a 1.2GB language pack per language).

: Uses advanced AI to automatically detect speech and align text segments with the exact pacing of your audio.