Self-hosted pyannote vs built-in diarization: when each makes sense

Diarization assigns speaker labels to audio segments without knowing who the speakers are. Here is how voice prints work, why similar vocal profiles cause problems, and how merge thresholds control the output.

An honest comparison of the four speech-to-text providers most documentary editors actually use, scored on accent handling, diarization, latency, and cost per hour of audio.

Word error rate is the standard accuracy metric, but it understates the problems that matter most for documentary audio: proper nouns, accents, crosstalk, and technical terms. Here is what WER measures and what it does not.