Transcription

How recordings become accurate transcripts.

Written By Ben O'Nion

Last updated 27 days ago

Recordings are transcribed using AssemblyAI's Universal-2 speech model. Universal-2 produces highly accurate, speaker-separated transcripts with strong handling of proper nouns, formatting, and real-world meeting audio β€” the foundation everything else is built on. Your meeting's transcript language follows the spoken language you set in Meeting bot rules.