EveryZing creates a text index of the audio data from audio and video files, using the industry's leading speech-to-text technology from BBN Technologies, to enable search within the spoken words of media, not just within the metadata. Most media search sites provide directories of audio and video by subject, category, or they search only the metadata provided by the creator of the media.
EveryZing takes search a step further by searching the spoken words inside the media in order to find more specific and relevant results. The text-based search results include snippets from the audio and video portion to help you figure out if the result is relevant. You can even click on the words to begin playing the media from that exact point.
EveryZing's solutions include audio and video channel indexing using everyday speech-to-text automatic transcription, which is mediocre but functional. (There's quite a few mistakes, but not unexpected.)
Decent features, targeted at businesses that are media-rich, sure; for the casual user, it's simply not accessible, which is disappointing.
While a corporate Web site may offer their EveryZing utilities to the public for free, the service itself from EveryZing is not; those companies have to pay dearly for something that can already be done using a combination of free software, and it's entirely closed off to the end user (so if you want to transcribe your favorite vids or lecturecasts, you're doing it by hand for the moment).