Video Insights From Your Azure Subscription, Ready to Redact
Azure AI Video Indexer is Microsoft's media AI service. Connected to Redactor, it becomes one of the paths AI processing can run on. Media is submitted to your own Azure subscription, and a timed transcript and detected objects come back against each item, ready for search and for redaction. Several further insights run on this path only: speakers named by voice profile, inferred topics, scene labels, brands, public figures, emotional tone and profanity filtering. Media is processed in the region your Azure account is bound to.
How it connects
AI processing runs on one of two provider paths, and the choice is a deployment decision with a data-residency consequence. On the VIDIZMO Indexer path, processing happens on your own infrastructure and content does not leave it. On the Azure AI Video Indexer path, you supply your own Azure subscription, the platform calls the service over its REST API, and media is processed in that subscription's region.
Media goes out for processing and results come back as timed data: a transcript aligned to the timeline so every word is a jump point, and detected objects as tracks that resolve to a moment. Both are indexed and searchable against the item, and both are what Redactor works from.
The insights that depend on this path come back the same way. Speakers are identified by name where the service holds a voice profile for them. Topics are inferred and mapped onto the IPTC taxonomy with a confidence figure. Brands are identified where they appear or are mentioned, and profanity in the transcript is identified and filtered.
What you can do together
- Find a spoken name or address by reading rather than listening in Redactor: search the transcript, select the words, and the audio segment inherits the timing, ready to silence or beep.
- Review every detected person, vehicle or identity document as a track across the timeline in Redactor, merge duplicates, adjust boxes, delete false positives and draw what the detector missed.
- Jump to a named speaker's remarks in a long recording, where the service holds a voice profile for that speaker.
- Redact a brand where it appears on screen or is mentioned in speech, since brands are identified and redactable in Redactor.
- See profanity identified and filtered in the transcript before a copy goes out.
A scenario
- SetupIT connects the county's Azure subscription and selects Azure AI Video Indexer as the processing provider.
- Morning after the meetingA four-hour board recording is uploaded to Redactor. It goes to Azure AI Video Indexer in the county's Azure region. A timed transcript, object tracks, the board members' names against their remarks, inferred topics and flagged profanity come back against the item.
- 10:15A records request arrives for the public-comment segment. The clerk searches the transcript for the street address one speaker read aloud, selects the words, and sets the segment to silence.
- 10:30In the studio, the people detected in the audience shots appear as tracks. She merges two tracks the detector split for one attendee, and draws a box around a child it missed.
- 10:45She jumps to one board member's remarks by name to confirm the segment boundaries, reviews the filtered profanity in one public comment, and exports the redacted rendition. The original stays under the output policy set for the job.
- ThroughoutThe recording was processed in the county's Azure region, and the transcript, tracks and topics now sit with it in the library.
What stays where
Azure AI Video Indexer stays in your subscription
The account, the region and the billing are yours.
Redactor reads timed data
Media goes to your subscription for processing; a transcript, detections and the further insights come back and are indexed against the item. Redaction, review and export happen in Redactor.
Nothing is replaced
The VIDIZMO Indexer path remains available, and on it content never leaves your environment. The provider is a deployment decision, not a rebuild.
Where processing runs
In the Azure region your account is bound to. A disconnected deployment uses the VIDIZMO Indexer path, where transcription and detection run on local models and the insights that depend on Azure AI Video Indexer are not available.
Products and solutions
Next step
See it on your own Azure AI Video Indexer instance. We will show the connection made, the data moving and the output, then size it for your deployment.
Request a demonstration or write to sales@vidizmo.ai
sales@vidizmo.ai · vidizmo.ai/integrations/catalog/azure-ai-video-indexer