#Adding to the voice pipeline?

1 messages · Page 1 of 1 (latest)

novel rock
#

Is there a way I can add steps before and after piper?
I want to do some text massaging prior, and then pass the output stream thru another process (sox) before it gets sent to the speakers?

I have been playing with the CLI and I want to achieve this type of pipeline in HA

cat in.txt | tr '\n' ' ' | sed 's/\.\s/. [[ . . . . ]]/g; s/\.$/. [[ . . . . ]]/; s/,\s/, [[ . ]]/g;' | piper --model /Users/jcd/repos/piper1-gpl/test_output/epoch-3757.onnx --output-raw | sox  -t raw -r 22050 -e signed-integer -b 16 -c 1 - -d norm -1.5 reverb 40 50 40
patent lion
novel rock
#

ok. thanks for your answer