Only institution-level Administrators have access to this feature toggle.
EchoVideo has partnered with several transcription service companies to provide an automatic speech recognition (ASR) service. The ASR service provides machine-generated automatic transcriptions for video / audio media. Once transcribed, the media can be played back with the transcription panel open, allowing users to both read and hear the text of the speech in the media.
Currently there are two triggers for automatic media transcription:
- When the item is added to or edited in EchoVideo (this article)
- When the item is published to an EchoVideo course
In EchoVideo, whenever media is added to the system, it is sent through the media processor. If the ASR All New Media feature is turned on, the MP3 file that comes OUT of the media processor is sent through the ASR Service provider and receives machine-generated transcripts. This process is important to know because it means that if this feature is enabled, all of the following file generation methods will trigger a request for automated transcripts:
- Media upload (by any user)
- New capture (by any method, including scheduled and ad hoc appliance captures and Universal Capture Software recordings)
- Media Edit and Save
- Media Edit and Save As
Regarding the last two bullets - editing and saving the media - the assumption is that any edit to the video / audio file will likely change the audio (.mp3) for the file. This means that even if the media being edited already HAS an automated transcript, the change in the .mp3 file generates a new request because it is generating a new mp3 file. The new file is the one sent to be transcribed.
In addition to the above listed methods, reprocessing media can send a request for automated transcripts, because processing generates an .mp3 file. IF, however, the media already HAS an automated transcript, and the media has not changed (the audio file is identical), reprocessing will NOT trigger a new transcript request.
Administrators can also request transcripts for individual media if necessary.
Providing transcriptions for all new media allows you to more easily apply closed captions to video / audio media by reviewing and editing the transcript then applying it as closed captions. In this case, you know that all media in the system has transcripts to work with. Alternately, if you find that your ASR transcripts are normally quite accurate, you can configure EchoVideo to automatically apply ASR transcripts to the closed captions track, if they meet a set confidence score.
To request automatic transcriptions for ALL new/reprocessed media
- Log into EchoVideo as an administrator.
- Click the Settings icon in the upper-right corner of the screen.
- From the Settings menu, select Institution Settings.
General settings appears and Basic Info is selected by default.
- Select Features from the options, as shown in the below figure.
- Under Transcripts and Captions, click the toggle to turn the ASR All New Media feature on or off. It is OFF by default.
- Review the warning message that appears and click Confirm.
NOTE: There is no override for the ASR All New Media feature toggle. It is either enabled or disabled for all media generated or edited by all users in the Institution. When enabled, any new media that is created on the tenant will be transcribed, regardless of the ASR Course Media toggle setting.
See Automatic Transcriptioning Service or ASR for additional details surrounding the automatic transcription service. See Using the EchoVideo Transcript Editor for more information and documentation to provide users for editing transcripts. If you also enable the Auto Send Transcripts to the Closed Caption Track feature, transcripts with confidence scores that meet or exceed the set level will also automatically be visible as closed captions on the media.