I just uploaded the code of my voice and text pipeline on Github after carefully reviewing and updating its readme for few days.
This project was born in 2018, and until now I’ve used it only for myself. I must thank @CCOSTAN because his HA Config was (probably still is) the best config ever documented, and for somebody like me that long time ago started usingHA, reading his code was a blessing!
Thank you!
During all these years I’ve updated and improved it. There’s little from the original version and It can be challenging for someone new to it to get it working, but if you would read the files inside you would see that it really isn’t too difficult and it’s actually easy to make it yours.
I will improve the documentation so that anybody will be able to modify it according to their needs!
I leave you to it, and the more advanced users can surely find their way and use it straight away!
– Link to the text and voice pipeline config –
Update:
An example of what this pipeline does is below. You can use this action in your automation and get the ball rolling!
You can set the volume, use an LLM, use any TTS you have configured, make the text dynamic or use a preconfigured text. It’s versatile!
There are more examples in the repository readme!
- action: script.uns
data:
kind: voice
message: Dinner is ready!
player: office
engine: google