I would like to be able to use my micro on a watson workspace to input text. Later on, my APP can pickup that text, use IBM Speech to text tools, and use it inside the flow of my app.
Basically, on node-red we have a "micro" that can be used as input on your browsers, and pass the audio to a node that converts de audio on a message, and then to another node that puts the message on the watson space or to any other flow or action.. Why do not allow to have a similiar feature on the WW interface ?
Add an icon of a Micro on the type area, near the "Upload file" , that allows to record and upload the wav, and then allow any app to pickup an process that audio !!
BTW, it would be fantastic it you also add the avaiability to an app to do an automatic audio out... (using the text to speech Watson APIs.....)
Please sign in to leave a comment.