Fact · Voice privacy and security
Microsoft says a customer can set a retention time for generated transcription text files with a parameter called timeToLive.
Checked against its source on October 17, 2026
In the source's own words
“Customers may set a retention time for generated transcription text files by using a parameter called "timeToLive".”
Data, privacy, and security for Speech to text, Microsoft, Microsoft Learn, 2026, How does speech to text process data? Batch transcription.
Open the original- What it measures
- The parameter applies to the transcript files, which are the generated text. Microsoft points developers to its batch transcription configuration reference for the details.
- What it does not show
- The page names timeToLive for generated transcription text files. It does not state a default retention period for the audio input.