Fact · Voice privacy and security
Microsoft documents that for real-time speech to text in Azure, audio is processed only in server memory and no data is stored at rest.
Checked against its source on October 16, 2026
In the source's own words
“For real-time speech to text, audio input is processed only on the Azure's server memory, and no data is stored at rest”
Data, privacy, and security for Speech to text, Microsoft, Microsoft Learn, 2026, Real-time speech to text.
Open the original- What it measures
- This applies to the Azure business service. Batch transcription has different storage terms.
- What it does not show
- Applies to Azure AI Speech, not consumer Windows dictation or Microsoft 365.
Source
Cited on
- Speech to Text Privacy: Where Your Voice GoesTopic
- Speech-to-Text APIs Compared: Price, Accuracy, SpeedGuide
- Voice Data Retention: What Apple, Google and Microsoft KeepGuide
- Copilot Voice and Dictation on WindowsGuide
- Dictation for Lawyers: Privilege and ConfidentialityGuide
- Windows Dictation Privacy and Online Speech RecognitionGuide
- Do cloud speech-to-text APIs store your audio?Question
- Does Azure speech to text store your data?Question
- How do you use the Azure Speech-to-Text API?Question
- Is voice to text GDPR compliant?Question
- Zero data retention (ZDR)Glossary