So after implementing this, if a prompt has been sent by a user sitting inside a VC.
The bot will generate the response, prepare a Female TTS voice using [gtt] library.
It will then join the VC where the user is present and will just give the sound output and the user can listen the answer of its
question (prompt). After the response is completed the bot will, disconnect and then also send the text like it does.
If the user is not in VC, the bot will work normally like it used to do earlier.
However this feature is a BETA feature, there are some more things that should be looked and checked before releasing into the public. I use this feature in my bot therefore I thought to contribute as well.
The bot will generate the response, prepare a Female TTS voice using [gtt] library.
It will then join the VC where the user is present and will just give the sound output and the user can listen the answer of its question (prompt). After the response is completed the bot will, disconnect and then also send the text like it does.
If the user is not in VC, the bot will work normally like it used to do earlier.
However this feature is a BETA feature, there are some more things that should be looked and checked before releasing into the public. I use this feature in my bot therefore I thought to contribute as well.