{{ searchResult.published_at | date:'d MMMM yyyy' }}

Loading ...
Loading ...

Enter a search term such as “mobile analytics” or browse our content using the filters above.


That’s not only a poor Scrabble score but we also couldn’t find any results matching “”.
Check your spelling or try broadening your search.


Sorry about this, there is a problem with our search at the moment.
Please try again later.

ear trumpetVideo and SEO are not a match made in heaven. Sure, you can title videos and tag them to make them more findable. But unless they're surrounding by plain dumb text (ambrosia to search engine spiders and crawlers), online video just isn't that findable.

A time-honored and time-consuming solution to video SEO has been the dreaded transcript for videos that are heavy on the spoken word. But transcription is a tedious and resource intensive task you'd hesitate to assign to even the lowliest intern.

Google's on the case -- perhaps trying to solve the problem in an unexpected way.

It started back in summer 2008 when Google released the Google Elections Video Search gadget. Using speech recognition technology, users could search YouTube's Politicians channels for spoken content. As speech recognition indicates precisely when words are spoken in a video, you could cut to the chase and jump to the precise moment in a clip when the word or phrase is uttered.

Google itself admitted the technology, renamed Google Audio Indexing, was "far from perfect...in one video Barack Obama on the 40th Anniversary of the Prague Spring, 'Czechoslovakia' is incorrectly detected as 'tech also but there', 'free' is replaced by 'forty' and there are many other mistakes."

Yet it seems Google's working on its voice recognition software is a somewhat unexpected channel, Google Voice. When users receive voicemail messages on the service, those messages are transcribed and emailed to the message recipient using, of course, voice recognition software. And recipients are encouraged to supply feedback on the accuracy of those transciptions via a "transcript useful?" checkbox on their messages.

The technology is still far from perfect. Some of my recent messages contain runes such as, "it's not a sorry I'm calling from now on that age" and "Joey sent me the funniest postcard in administers the lines that adventure loan and corrupt Assisi, right." Often, you have to hit the play button to listen to the actual audio.

But consider the possibilities. Once this starts working - no mean feat, but it's getting better - Google will have a stunning edge in video search, and YouTube's supremacy (it's already the #2 search engine after Google itself) will be cemented for some time to come. Podcasts and other audio media, perhaps even songs, will also be transcribleable, and hence searchable.

It seems unlikly on the surface, but upon reflection it makes perfect sense. Google is using Google Voice to help usher in a revolution in multimedia search engine optimization.

Rebecca Lieb

Published 25 February, 2010 by Rebecca Lieb

Rebecca Lieb oversees Econsultancy's North American operations.

Follow me on Twitter, or connect with me on Facebook.

160 more posts from this author

Comments (2)


Brian Northway

A company called Virage pioneered this technology a decade ago and is far better at it.  Even so, a quick watch-through by a human to correct the errors (like ya do with OCR) would make this tech usable now on YouTube.

over 6 years ago


Yuotube fanatic

It seems Google have some exciting things in the pipeline when it comes to video. The voice recognition really excites me and could really change the way seo's think about youtube marketing.

over 6 years ago

Save or Cancel

Enjoying this article?

Get more just like this, delivered to your inbox.

Keep up to date with the latest analysis, inspiration and learning from the Econsultancy blog with our free Daily Pulse newsletter. Each weekday, you ll receive a hand-picked digest of the latest and greatest articles, as well as snippets of new market data, best practice guides and trends research.