LA Times technology columnist David Colker tested podcast search engines in Thursday's column. Both PodZinger and Blinkx use speech recognition technology, scanning the web for audio and video files on RSS feeds and translating the audio content into a text file that can then be searched.

The conversion process can take up to one hour for a 45-minute audio file, according to Alex Laats at PodZinger. Around 100,000 audio files from commercial and public sector sites have been indexed by both PodZinger and Blinkx, although Blinkx has indexed more broadcast content than output from blogs.

Both services are free. Neither search offers full transcripts in search results due to rights restriction, and some search results are inaccurate due to misinterpretation by the speech recognition tools. Mr Colker found some phonetic searches to be more accurate.

"A PodZinger search on the wine 'Pinot Noir' found the podcast series 'Grape Radio'," wrote Mr Colker.

"On the audio stream, the announcer talked about an area 'too far north to grow vines, especially varieties like Riesling and Pinot Noir'. PodZinger translated it as 'two foreign office two Croat specialty varieties like Riesling and Pinot Noir'.

"Still, the fact that the audio tracks of podcasts and videos are now searchable is mighty impressive. I look forward to someone figuring out how to get the Web to make the sound of one hand clapping."

Free daily newsletter

If you like our news and feature articles, you can sign up to receive our free daily (Mon-Fri) email newsletter (mobile friendly).