-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to implement voice input #1
Comments
The best user experience could actually be such that the user opens a call to the bot, says their message and pauses for X duration, or says "over" after a slight pause or something like that. Then the bot processes this message and answers with text-to-speech. This would actually result in improved privacy as call contents are not recorded anywhere. |
The user could even state in the end of the call if they actually do want to save a recording, and the bot would confirm this and then provide a recording after call ends. |
The addition of text-to-speech would be relatively trivial, but the harder problem is getting voice input working as seamlessly as possible. Ideally I would do this with Calls plugin but I'm not at all familiar with it yet.
The text was updated successfully, but these errors were encountered: