Desktop endpoint
Local audio capture, transcription, and meeting history on the employee’s Windows device.
Sitr by Wislab ستر
Security and architecture
Where does meeting data go?
A high-level view of how meeting content moves through Sitr before you decide whether the deployment fits your controls.
Can our reviewers follow the meeting-content path?
Audio stays on the device. Transcript text moves to your processing server for summaries.
Meeting audio is captured and transcribed on the employee’s Windows device. The finalized transcript is sent to the processing server your organization operates, which returns a generated summary to the desktop.
1
Capture and transcribe locally
Meeting audio is recorded and transcribed on the employee’s device.
Transcript text
Meeting audio
2
Summary is generated
Your organization’s processing server analyzes the transcript and produces a meeting summary.
3
Result returns to the desktop
The completed summary is saved with the local meeting record on the employee’s device.
Important
Meeting audio is not uploaded for summarization. Transcript text is intentionally sent to your processing server—this is narrower than claiming that all meeting content stays on one device.
Which systems are involved?
Desktop, Portal, and processing server are separate trust boundaries.
Organization-operated AI processing does not mean the Wislab Portal is absent from account authentication.
Operated by Wislab
Account Portal
Access tokens
No meeting content
Operated by the user’s organization
Desktop endpoint
Transcript text
Completed summary
Operated by your organization
Processing server
Account Portal
Account sign-in and desktop authentication. Does not receive meeting audio or transcript content.
Processing server
Transcript analysis and summary generation on infrastructure your organization selects and operates.
What will our security team ask first?
Direct answers to the architecture questions.
Where is audio processed?
Audio is captured and transcribed on the user’s Windows device. The summary workflow sends transcript text to the configured processing server and does not send the audio file.
Where are transcripts stored?
Transcripts are stored locally on the desktop and are also processed as part of the summary job on the organization-operated processing server. Retention on both systems must be considered.
Can Wislab access our meeting content?
Wislab does not receive meeting audio or transcript text through the Wislab-operated Portal in the current architecture. Meeting content stays on your desktop endpoints and processing server.
Can our organization host the AI processing server?
Yes. That is the current deployment model. Your organization supplies and operates the processing server and configures each desktop with its reachable server URL.
Does the architecture satisfy your first review?
The next step is a technical discussion covering your network, endpoint, identity, retention, and pilot requirements.