The Echo not only allows you to extend its vocabulary, Amazon offers the Echo functionality as as a service that any developer can use from their own hardware.

If you wanted to use your own voice recognition and natural language processing, you could easily tie that into open source vocabulary that has been written for Echo.

Yea, i hear the API is quite good - i should have been more clear, it sounds like for me the main blocker is the trigger word.

But yea, what i would want is to literally take all input from the Echo, have amazon/echo transcribe it to text, and then send it to my code. Echo would then read the english response back.

Sorry, I might be totally off the base here but why not use IBM Watson for that? It's free for a thousand minutes in a month and it's speech-to-text looks quite good on the first glance.

I was just looking around for a custom solution to have something listening, send it off somewhere to get the text out of the voice command and then respond to keywords/contexts with appropriate custom-made actions. All you need then is to process that and read out the response.

No idea, does IBM Watson have a good in-home hardware device?

I'm not talking about using Echo to do any complex work, i want echo to just be my middle man taking in speech and sending my program the text. With of course, a customizable wake word.

I wasn't aware of IBM Watson having an Echo or Home like device. If it matches my needs, i'm very interested :)