Oh wow, thank you!
I also saw a reference that this is all open-source but https://github.com/Picovoice/ does not have a Picovoice repository. Is it https://github.com/Picovoice/Porcupine?
Not sure what the plans for open sourcing the rest of the components are though.
1- Speech-to-Intent: It allows you to issue complex voice commands in a specific domain and in turn returns the intent. For example, in the case of a coffee maker you can say "Please may I have a single shot espresso with no milk and two sugars". The engine returns a JSON-like object with {"product": "espresso", "milk": "no", "sugar", "two", "# shots": "2"}. It is a tightly coupled domain-specific speech recognition and NLU. It is small (less than 3MB and 8% CPU usage on RPi3) and ideal for home automation, industrial application, service industry, etc.
2- Speech-to-Text: It is large vocabulary speech recognition software that runs locally. It will support all platforms currently being supported. It allows you to do large vocabulary transcription with high accuracy locally on an embedded platform.
It's apparently only talking about their benchmarking tool: https://github.com/Picovoice/stt-benchmark
The engine itself is called Cheetah, and appears to be a closed source, "inquire for pricing/licensing" product.