We are starting the process to build a desktop platform of various functionalities and need developers to help. As speech recognition is a part of that, we decided to post it here as a starting small step to help selecting development partners. Then we start building the main platform modules with you one at a time.
As for this application:
- On start, your application will start "listening"
- Your application will use windows built in speech to text (Windows Dictate) to convert speech to text.
- Your application need to have the structure to send converted text to another running application, we call it here the Main Platform (something like api).
- Your application will have the structure to receive responding text from the main platform.
- Your application should be able to convert received text to audio using microsoft built-in text to speech (windows Narrator), but instead of playing it, saving it as a wave file for the main platform to use it.
We expect to get the source code of the application with the application with all the functionalities working.
In the document and images below you will find more details about how your developed application need to work.