Project Description
I would need help to build a working project with following function
Browser -> capture voice based on audio context and continuous listening based on voice activity detection(not to use MDN speech synthesis as we need actual binary stream) -> use web socket to send the chunked binary data to server -> server should put the chunk together and send the complete voice to a API in PCM format -> API should call Bing speech to text API And convert speech to text and then the same text can be used by text to speech and played back on browser.
The whole project is expected to be build using HTML, Javascript and node js at the server.
For more details can be shared once the project is awarded