We have a web application steam video into Adobe Media Server 5.0.7 which is hosted on AWS, then a mechanism pick up the videos and transcode the f4v files into different video formats and then store on S3.
We would like to implement some sort of speech-to-text mechanism on the videos recorded for analysis. I have found the following section on "https://helpx.adobe.com/adobe-media-server/tech-overview/streaming-media.html"
You now deliver Adobe Extensible Metatdata Platform (XMP) metadata embedded video streaming through Adobe Media Server to Flash Player. XMP is a labeling technology that allows you to embed data about a file into the file itself. XMP metadata is a system that communicates critical media information from the point where the media is created to the point where media is viewed. With XMP, applications and publishing systems can capture, share, and leverage metadata. In Adobe Media Server, all the metadata embedded within a media file is accurately delivered. In addition, speech-to-text metadata embedded within files and encoded from Adobe Media Encoder CS4 can be delivered.
Can someone please point me to a direction on how to make it happen on Adobe Media Server?