Speech-to-text providers compared: Whisper, Deepgram, AssemblyAI, Google STT

A practical guide to transcribing interviews for documentary post: when AI is good enough, when human review is needed, how to handle speakers, timecode, and overlap.

Transcript-based editing means selecting interview clips by reading the words instead of scrubbing through audio. Here is why it dominates modern documentary post and how the workflow runs.

From dailies to final delivery: every stage a documentary passes through in post, what each stage produces, what it costs in time, and where things stall.