Glossary
Speaker diarization
Speaker diarization is the process of splitting an audio recording into segments and labelling which speaker is talking in each one.
What it means
Transcription answers "what was said." Diarization answers "who said it." The two are separate problems: a transcript can be perfectly accurate yet still read as one undivided wall of text. Diarization groups the audio into turns and assigns each turn to Speaker 1, Speaker 2, and so on. On its own, it usually cannot put real names to those labels.
Diarization is hardest when people talk over each other, or when several voices sound similar. A clean recording with separated audio sources makes it noticeably more reliable.
How this relates to Autorec
Autorec records the meeting to a clean audio track, which is exactly the input diarization needs to work well. Its on-device transcription produces a timestamped transcript that maps naturally onto speaker turns once you review it.
Try Autorec
A local-first meeting recorder for Linux and Windows. It auto-detects your calls, records to your own disk, and transcribes on your machine. One-time €20, with a free tier to start.
Download Autorec