Google Translate, DeepL, and OpenAI: which engine for documentary interviews?

How to handle proper nouns, speaker voice, and over-polish when sending documentary transcripts through machine translation, and when to flag a segment for a human reviewer.

How to choose between Deepgram, Google STT V2, AssemblyAI, and OpenAI realtime for live interview transcription. The key axes are latency, diarization quality, language coverage, and cost per minute.

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.