We are fairly new to RASA. However, I have been able to successfully create a conversational chat bot. Our next target is to make it voice enabled. That means, we would like to integrate a kind of voice agent to the chat bot. So, when a caller makes a phone call, the speech needs to be converted to Text (STT) and this text shall be fed into the conversational chat bot and the response (in text format) shall be converted back to speech (TTS) and shall be sent across to the caller. This way, the caller can actually speak to the chat bot (voice) instead of just texting it.
Has anyone attempted something like this? Or any ideas around this would certainly help us.
Thanks in advance.