Video Studio - Automatically detect different speakers in a recording - 3900.116
Impact: Instructors
Updated Help Page: Video Studio (Instructors)
Exchange ID: Not applicable
Video Studio can now automatically identify different speakers in a recording and individually segment them within the recording transcript. The feature can identify up to 30 speakers. Instructors can manually edit the speaker labels to better identify each individual for users.
The ability to automatically detect speakers and edit speaker labels enhances the accuracy and clarity of a recording transcript, making it more valuable to instructors and students alike.
Instructor
When instructors access a recording transcript, they will see that Video Studio automatically generates transcriptions segmented by speaker. The default label for each speaker is Speaker 0, Speaker 1, up to 30 speakers. Instructors can edit speaker labels the same way they can edit recording transcripts.
Image 1: Video Studio is now able to identify multiple speakers when it automatically generates captions and transcript. When generated, the speakers are identified from "Speaker 0" up to "Speaker 29."
Image 2: Video studio allows instructors to edit speaker label names in the transcript.
Administrator
Availability: Video Studio is a premium solution.
Activation: We are offering customers a free trial until June 30, 2025. This trial provides access to the full version of Video Studio. Video Studio is set to OFF as a default in test/stage and production environments. If you want to enable it in your institution’s environment, you can do that for free until the end of June 2025.
Configuration: To configure Video Studio: select Configure in The Ultra Experience is Here! module. Select Enable creating/uploading videos using Video Studio. Beyond June 30, 2025, your institution will have to purchase Video Studio to continue using it.