AI Audio Transcript with integration from replicate/whisper

Discuss
, ,
#1

Hello, i hope you can help me.

How can i program an app with the codes from this site in kodular:

I want to make an simple app were i can choose audio on my phone and make with the code above an transcript.

Thank you!

#2

Try the web component together with a Post request

curl --silent --show-error https://api.replicate.com/v1/predictions \
	--request POST \
	--header "Authorization: Bearer $REPLICATE_API_TOKEN" \
	--header "Content-Type: application/json" \
	--header "Prefer: wait" \
	--data @- <<-EOM
{
	"version": "3ab86df6c8f54c11309d4d1f930ac292bad43ace52d10c80d87eb258b3c9f79c",
	"input": {
      "audio": "https://replicate.delivery/pbxt/Js2Fgx9MSOCzdTnzHQLJXj7abLp3JLIG3iqdsYXV24tHIdk8/OSR_uk_000_0050_8k.wav",
      "batch_size": 64
	}
}
EOM

You can translate the curl command (taken from the documentation) using this tutorial

The audio file must be available somewhere in the internet, you might want to first upload it from your device

Taifun