Translating documentary interviews: practical notes for editors

How Google Translate, DeepL, and OpenAI translation handle tone, names, and idioms differently, and why the engine that works for corporate content is often wrong for documentary speech.

SRT is more widely supported. VTT has styling hooks. Here is what each format contains, which downstream tools expect which, and where mismatches cause dropped cues.

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.