Is this something doable? Or would that just be a "simple" script of sorts from HA? Or do you know of a docker that can achieve non-verbal sounds?
#Voice assistant and vocal sound effects like sneezing, and other mouth noises via voice model?
mint spruce
shell lynx
Orpheus TTS can do emotions and non verbal sounds like laughs and giggles. It can't be used with HA yet.
wheat blaze
Orpheus TTS can do emotions and non verbal sounds like laughs and giggles. It ca...
What do you mean with yet? Someone actually working on it to get it working? I have it implemented in HA using following
https://github.com/Lex-au/Orpheus-FastAPI
and
https://github.com/roryeckel/wyoming_openai
But as you said, it’s not working properly. After this solution split the responses in junks to allow streaming, in HA only the first piece is played and all follow up responses don’t. I hope HA will support this kind of streaming at any time.
