N8N + MP3 + Whisper Api

Hello, everyone.

Im trying to extract audio from a youtube video, but im have a problema.

This is the response that I received:
error:Prediction input failed validation: {“detail”:[{“loc”:[“body”,“input”,“audio”],“msg”:“Incorrect padding”,“type”:“value_error.”}]}

Hey @laschuk,

Which node is showing that error and can you sent the output of the HTTP Request node? My initial thought is the issue is with the data you are sending, You have "audio": "data:audio/oga;base64,{{ $json["link"] }}", but is $json[“link”] base64 encoded data? I also can’t see that as an option in the Replicate API docs.

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.