Sunday, October 5, 2008
Speech Output for Knol Articles

Google added text-to-speech capabilities to some Knol articles, like the one titled “
File Formats in Digital Photography”. You can download the MP3 as well as hit a Listen button in the top right. The quality of the speech output – I strongly suppose it’s all a software reading indeed, but asked Google for more background info in any case – is amazing. Macbeach in the comments at
Google Operating System writes, “This is the best text-to-speech I’ve ever heard."*
Knol’s help page on the subject explains, “We are experimenting with Audio Playback as an option for some knols, starting with a handful of English language featured knols ... If this experiment is successful, we may make Audio Playback available to more knols in additional languages, and additional features.”
Both text-to-speech as in Knol, and speech-to-text as in YouTube (experimental too right now, and only working with videos of some US politicians), offer the ability to add capabilities to an application which may convince some people to use it just for that feature. Here are some hypothetical use cases for outputting audio in Google’s apps:
- Read out aloud a Google Docs document, spreadsheet, or presentation
- Read a Gmail email
- Read a public domain book scanned as part of Google Book Search
- Automatically translate the audio track of YouTube videos; the parts needed would be transcription (Google already has speech to text in YouTube), translation (Google has machine translation systems, sometimes working OK, sometimes not so well), and then text-to-speech as in Knol
- Read web pages as part of Google Chrome
- Provide audio directions in Google Maps
- Provide the “Listen” widget for Blogspot blogs; this could also be used as a way to create machine-read podcasts
- and more
[Thanks Hebbet, via Google OS!]
>> More posts
Advertisement
This site unofficially covers Google™ and more with some rights reserved. You can subscribe to the feed, email your tips and join our forum!