Ask HN: Are there any free APIs that do speech transcription?

Posted by fatbat on Wednesday August 08, 2012 @05:38PM
from the ask-hn dept.

Like how Google Voice and Twilio offers Speech->Text on their services.

I have yet to find a API that does this. Is there a reason this is not available yet? Cost issues?

I suppose piggybacking of Twilio's API is the closest I found but it looks that feature cost $.05/min. :\

( 5 comments | 4 points | on HN )

Re:Ask HN: Are there any free APIs that do speech transcript... by fatbat on Wednesday August 08, 2012 @08:36PM (#4358890)

So I continued my search and veered into iOS integrations which I should have mentioned was my initial intention.

This may interest some,

http://www.politepix.com/openears/ (free + does not need network) http://cmusphinx.sourceforge.net/

I think that no-network piece is vital since alot of the solutions require a ping to the server because of sheer vocabulary limitation. Hope that helps!

[ Parent | on HN ]

Re:Ask HN: Are there any free APIs that do speech transcript... by irunbackwards on Wednesday August 08, 2012 @06:01PM (#4358326)

I found this on Quora, looks like it's up your alley, and there is a free trial: http://koemei.com/pricing

Also, this gentleman talks about accessing the undocumented Google Speech API: http://mikepultz.com/2011/03/accessing-google-speech-api-chr...

[ Parent | on HN ]

Re:Ask HN: Are there any free APIs that do speech transcript... by koopajah on Thursday August 09, 2012 @03:48AM (#4360032)

You can use the speech API of google but if you plan to build an app/product on it you'll be detected/blocked quickly

[ Parent | on HN ]

Re:Ask HN: Are there any free APIs that do speech transcript... by leebossio on Friday August 17, 2012 @04:16PM (#4398557)

Have you tried this?

[ Parent | on HN ]

Re:Ask HN: Are there any free APIs that do speech transcript... by koopajah on Thursday August 09, 2012 @03:54AM (#4360044)

Speech->Text conversion is really harder than simple Voice Recognition. There are not a lot of companies doing this right now the most famous being Nuance and Google of course. Nuance has been acquiring a lot of companies the last three years that were doing a lot of improvements to the technologies (SVOX, VLingo, etc.) and powers Siri technology.

[ Parent | on HN ]