You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The idea is to allow the API to host a local api server. in which another script and send an request to it and the app returns back an generated voice.mp3 file
More information
This is basically so that people can use the great Speech to Speech system on this app to create a Text to Speech (TTS) API easily. I'm assuming that this app already uses a Speech To Text (STT) module to translates the words being spoken into text, then for the TTS module to create a voice file that gets played. I don't know how this app works. But I assume that's how it works.
So it could be as simple as getting the local API server to ignore the STT part and send the request straight to the TTS module that can send back an audio file of the speech.
Soo in simple terms this is a diagram.
Post Request (for a TTS to) --> Local API Server ---> (Posts request to call) TTS Module ---> (returns) Audio file ---> (returns back to the request)
A person can make an script that sends an request to the api server, locally hosted by the App. And the request could look something like this:
In a few words, describe your idea
The idea is to allow the API to host a local api server. in which another script and send an request to it and the app returns back an generated voice.mp3 file
More information
This is basically so that people can use the great Speech to Speech system on this app to create a Text to Speech (TTS) API easily. I'm assuming that this app already uses a Speech To Text (STT) module to translates the words being spoken into text, then for the TTS module to create a voice file that gets played. I don't know how this app works. But I assume that's how it works.
So it could be as simple as getting the local API server to ignore the STT part and send the request straight to the TTS module that can send back an audio file of the speech.
Soo in simple terms this is a diagram.
Post Request (for a TTS to) --> Local API Server ---> (Posts request to call) TTS Module ---> (returns) Audio file ---> (returns back to the request)
A person can make an script that sends an request to the api server, locally hosted by the App. And the request could look something like this:
This is in javascript. And the app could have an option for the developer to enable this local api server.
Thanks, cassitly
The text was updated successfully, but these errors were encountered: