Skip to content

Understand supported transcription modes and credit usage.

Video To Text bills transcription by media duration. The stored media duration keeps millisecond precision, but billing rounds the duration to the nearest second before calculating credits.

ModeCredits
balanced1 credit per minute
precision2 credits per minute

Credits are based on the media duration and the selected mode. Video To Text rounds the media duration to seconds, then applies the mode’s per-minute credit rate.

For example, a 90.4 second file is billed as 90 seconds. A 90.5 second file is billed as 91 seconds.

Task responses include billedCredits, which shows the actual credits used for that transcription task.